Project ID

2024-25_ML_001

2024-25_ML_002

2024-25_ML_003

2024-25_ML_004

2024-25_ML_005

2024-25_ML_006

2024-25_ML_007

2024-25_ML_008

2024-25_ML_009

2024-25_ML_010

2024-25_ML_011

2024-25_ML_012

2024-25_ML_013

Project ID

2024-25_ML_014

2024-25_ML_015

2024-25_ML_016

2024-25_ML_017

2024-25_ML_018

2024-25_ML_019

2024-25_ML_020

2024-25_ML_021

2024-25_ML_022

2024-25_ML_023

2024-25_ML_024

2024-25_ML_025
Title

Characterizing Disease Progression in Parkinson’s Disease from Videos of the Finger Tapping Test

A Self-Labeling Method for Adaptive Machine Learning by Interactive Causality

Machine Learning Analysis of Human Skin by Optoacoustic Mesoscopy for Automated Extraction of Psoriasis and Aging B

Machine Learning on Multiplexed Optical Metrology Pattern Shift Response Targets to Predict Electrical Properties

Enhancing SSVEP-BCI Performance Under Fatigue State Using Dynamic Stopping Strategy

Epileptic Seizure Detection Based on Path Signature and Bi-LSTM Network With Attention Mechanism

Multi-Task Heterogeneous Ensemble Learning-Based Cross-Subject EEG Classification Under Stroke Patients

Real-Time Precise Targeting of the Subthalamic Nucleus via Transfer Learning in a Rat Model of Parkinson’s Disease Bas

Performance Assessment of an ITU-T Compliant Machine Learning Enhancements for 5G RAN Network Slicing

Multitask and Transfer Learning Approach for Joint Classification and Severity Estimation of Dysphonia

A Hybrid Air Quality Prediction Model Based on Empirical Mode Decomposition

Knee-Point-Conscious Battery Aging Trajectory Prediction Based on Physics-Guided Machine Learning

Privacy-Preserving Federated Class-Incremental Learning

Title

Analysis of Brain Imaging Data for the Detection of Early Age Autism Spectrum Disorder Using Transfer Learning Approa

Deep Learning for Electromyographic Lower-Limb Motion Signal Classification Using Residual Learning

Navigation Learning Assessment Using EEG-Based Multi-Time Scale Spatiotemporal Compound Model

AI-Based Advanced Approaches and Dry Eye Disease Detection Based on Multi-Source Evidence: Cases, Applications, Iss

Semi-Supervised Learning for Multi-Label Cardiovascular Diseases Prediction: A Multi-Dataset Study

KFDAE: CircRNA-Disease Associations Prediction Based on Kernel Fusion and Deep Auto-Encoder
Graph Neural Network-Based EEG
Classification: A Survey
B2-ViT Net: Broad Vision Transformer Network With
Broad Attention for Seizure Prediction
Multi-Scale Masked Autoencoders for Cross-Session
Emotion Recognition
Multi-Task Collaborative Network: Bridge the Supervised and
Self-Supervised Learning for EEG Classification in RSVP Tasks
Physiologic Network-Based Brain-Heart Interaction Quantification During Visual Emotional Elicitation

An Overview of the ADReSS-M Signal Processing Grand Challenge on Multilingual Alzheimer's Dementia Recognition Th
 Domain

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Domain

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning

Machine Learning
Project ID
2024-25_DL_001
2024-25_DL_002
2024-25_DL_003
2024-25_DL_004
2024-25_DL_005
2024-25_DL_006
2024-25_DL_007
2024-25_DL_008
2024-25_DL_009
2024-25_DL_010
2024-25_DL_011
2024-25_DL_012
2024-25_DL_013
Project ID
2024-25_DL_014
2024-25_DL_015
2024-25_DL_016
2024-25_DL_017
2024-25_DL_018
2024-25_DL_019
2024-25_DL_020
2024-25_DL_021
2024-25_DL_022
2024-25_DL_023
2024-25_DL_024
2024-25_DL_025
Title
Deep Learning-Based Assessment Model for Real-Time Identification of Visual Learners Using Raw EEG
From Forearm to Wrist: Deep Learning for Surface Electromyography-Based Gesture Recognition
Physics-Informed Deep Learning for Muscle Force Prediction With Unlabeled sEMG Signals
Deep Statistical Solver for Distribution System State Estimation
Bad and Good Errors: Value-Weighted Skill Scores in Deep Ensemble Learning
Dependency-Aware Dynamic Task Offloading Based on Deep Reinforcement Learning in Mobile-Edge Computing
Deep Metric Learning With Locality Sensitive Mining for Self-Correcting Source Separation of Neural Spiking Signals
An Introduction to Adversarially Robust Deep Learning
Cancellable Deep Learning Framework for EEG Biometrics
Automatic Detection of Scalp High-Frequency Oscillations Based on Deep Learning
Deep Q-Learning-Based Molecular Graph Generation for Chemical Structure Prediction From Infrared Spectra
DNN Assisted Projection Based Deep Reinforcement Learning for Safe Control of Distribution Grids
DiffMDD: A Diffusion-Based Deep Learning Framework for MDD Diagnosis Using EEG
Title
From Clustering to Cluster Explanations via Neural Networks
Deep Prior-Based Audio Inpainting Using Multi-Resolution Harmonic Convolutional Neural Networks
Multi-Agent Double Deep Q-Learning for Fairness in Multiple-Access Underlay Cognitive Radio Networks
Association Between Sleep Quality and Deep Learning-Based Sleep Onset Latency Distribution Using an Electroencephalogra
Deep Knowledge Tracing Incorporating a Hypernetwork With Independent Student and Item Networks
Learning Energy-Efficient Transmitter Configurations for Massive MIMO Beamforming
Learning Ordinal–Hierarchical Constraints for Deep Learning Classifiers
Deep Reinforcement Learning-Based Robust Design for an IRS-Assisted MISO-NOMA System
GMILT: A Novel Transformer Network That Can Noninvasively Predict EGFR Mutation Status
Deep Learning-Based DOA Estimation
Multi-Modal Sleep Stage Classification With Two-Stream Encoder-Decoder
Robust Network Slicing: Multi-Agent Policies, Adversarial Attacks, and Defensive Strategies
 Domain
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Domain
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
Deep Learning
 Project ID

2024-25_DM_001

2024-25_DM_002

2024-25_DM_003

2024-25_DM_004

2024-25_DM_005

2024-25_DM_006

2024-25_DM_007

2024-25_DM_008

2024-25_DM_009

2024-25_DM_010

2024-25_DM_011

2024-25_DM_012

2024-25_DM_013

Project ID

2024-25_DM_014

2024-25_DM_015

2024-25_DM_016

2024-25_DM_017

2024-25_DM_018

2024-25_DM_019

2024-25_DM_020
2024-25_DM_021

2024-25_DM_022

2024-25_DM_023

2024-25_DM_024

2024-25_DM_025

2024-25_DM_026

2024-25_DM_027

Project ID

2024-25_DM_028

2024-25_DM_029

2024-25_DM_030

2024-25_DM_031

2024-25_DM_032

2024-25_DM_033

2024-25_DM_034

2024-25_DM_035

2024-25_DM_036

2024-25_DM_037

2024-25_DM_038

2024-25_DM_039

2024-25_DM_040

2024-25_DM_041
 Project ID

2024-25_DM_042

2024-25_DM_043

2024-25_DM_044

2024-25_DM_045

2024-25_DM_046

2024-25_DM_047

2024-25_DM_048

2024-25_DM_049

2024-25_DM_050

2024-25_DM_051

2024-25_DM_052

2024-25_DM_053

2024-25_DM_054

2024-25_DM_055
Title Domain

Gender-Based Analysis of User Reactions to Facebook Posts Datamining

Deep Learning-Based Assessment Model for Real-Time Identification of Visual Learners

Datamining
Using Raw EEG
An Improved Extreme Learning Machine (ELM) Algorithm for Intent Recognition of
Datamining
Transfemoral Amputees with Powered Knee Prosthesis
Analysis of Cancer-associated Mutations of POLB using Machine Learning and
Datamining
Bioinformatics

BIOWISH: Biometric Recognition Using Wearable Inertial Sensors Detecting Heart Activity Datamining

Bad and Good Errors: Value-Weighted Skill Scores in Deep Ensemble Learning Datamining

Classification of Tolerances in Permanent Magnet Synchronous Machines With Machine

Datamining
Learning
A Cost-Sensitive Machine Learning Model With Multitask Learning for Intrusion Detection
Datamining
in IoT
An IoMT-Based Incremental Learning Framework With a Novel Feature Selection
Datamining
Algorithm for Intelligent Diagnosis in Smart Healthcare

Applying Competition-Based Learning to Stimulate Students’ Practical and Competitive AI

Datamining
Ability in a Machine Learning Curriculum

Exploring Classification of Topological Priors With Machine Learning for Feature Extraction Datamining

Multilayer Perceptron Neural Network Approach to Classifying Learning Modalities Under

Datamining
the New Normal
E- Commerce Fraud Detection Based on Machine Learning Techniques Systematic
Datamining
Literature Review

Title Domain

An Intelligent Big Data Security Framework Based on AEFS-KENN Algorithms for the
Datamining
Detection of Cyber-Attacks from Smart Grid Systems

Deep Ensemble Learning With Pruning for DDoS Attack Detection in IoT Networks Datamining

A Novel Recommendation Algorithm Integrates Resource Allocation and Resource Transfer

Datamining
in Weighted Bipartite Network

Vaccine Hesitancy Hotspots in Africa: An Insight From Geotagged Twitter Posts Datamining

Forecasting Gender in Open Education Competencies: A Machine Learning Approach Datamining

A Cost-Sensitive Machine Learning Model With Multitask Learning for Intrusion Detection
Datamining
in IoT

A Multi-perspective Fraud Detection Method for Multi-Participant E-commerce Transactions Datamining

FRHIDS: Federated Learning Recommender Hybrid Intrusion Detection System Model in
Datamining
Software-Defined Networking for Consumer Devices

Attention-Based Hybrid Deep Learning Model for EEG Emotion Recognition Datamining

SAFER-STUDENT for Safe Deep Semi-Supervised Learning With Unseen-Class Unlabeled

Datamining
Data

The Extent of AI Applications in EFL Learning and Teaching Datamining

Applying Competition-Based Learning to Stimulate Students’ Practical and Competitive AI

Datamining
Ability in a Machine Learning Curriculum
Extensible Machine Learning for Encrypted Network Traffic Application Labeling via
Datamining
Uncertainty Quantification

Hybrid Models for Knowledge Tracing: A Systematic Literature Review Datamining

Title Domain

Multi-Branch Mutual-Distillation Transformer for EEG-Based Seizure Subtype

Datamining
Classification

Multi-Modal Sleep Stage Classification With Two-Stream Encoder–Decoder Datamining

A Novel CNN-BiLSTM Ensemble Model With Attention Mechanism for Sit-to-Stand Phase
Datamining
Identification Using Wearable Inertial Sensors

An Introduction to Adversarially Robust Deep Learning Datamining

Deep Learning for Electromyographic Lower-Limb Motion Signal Classification Using

Datamining
Residual Learning
Deep Learning-Based Assessment Model for Real-Time Identification of Visual Learners
Datamining
Using Raw EEG

DiffMDD A Diffusion-Based Deep Learning Framework for MDD Diagnosis Using EEG Datamining

From Clustering to Cluster Explanations via Neural Networks Datamining

Improving Generalization of ML-Based IDS With Lifecycle-Based Dataset Auto-Learning

Datamining
Features and Deep Learning

Learning Random Access Schemes for Massive Machine-Type Communication With MARL Datamining

Machine-to-Machine Transfer Function in Deep Learning-Based Quantitative Ultrasound Datamining

Otago Exercises Monitoring for Older Adults by a Single IMU and Hierarchical Machine
Datamining
Learning Models

Physics-Informed Deep Learning for Muscle Force Prediction With Unlabeled sEMG Signals Datamining

Semi-Supervised Learning for Multi-Label Cardiovascular Diseases Prediction A Multi-

Datamining
Dataset Study
Title Domain

Stealthy Adversarial Attacks on Machine Learning-Based Classifiers of Wireless Signals Datamining

Targeted-BEHRT Deep Learning for Observational Causal Inference on Longitudinal

Datamining
Electronic Health Records

Test Input Prioritization for Machine Learning Classifiers Datamining

Unleashing the Potential of Knowledge Distillation for IoT Traffic Classification Datamining

A Weighted Stacking Ensemble Model With Sampling for Fake Reviews Detection Datamining

An Explainable and Resilient Intrusion Detection System for Industry 5.0 Datamining

Resource-Constraint Deep Forest based Intrusion Detection Method in Internet of Things for
Datamining
Consumer Electronic
Leveraging Gametic Heredity in Oversampling Techniques to Handle Class Imbalance for
Datamining
Efficient Cyberthreat Detection in IIoT

Micro-Expression Recognition Based on Nodal Efficiency in the EEG Functional Networks Datamining

High Precision Traffic Flow Reconstruction via Hybrid Method Datamining

Time-series Failure Prediction on Small Datasets Using Machine Learning Datamining

Application of Quantum Recurrent Neural Network in Low-Resource Language Text

Datamining
Classification

Pretrained Quantum-Inspired Deep Neural Network for Natural Language Processing Datamining

Self-Supervised Learning-Based General Laboratory Progress Pretrained Model for

Datamining
Cardiovascular Event Detection
13.75
Project ID
2024-25_DS_001
2024-25_DS_002
2024-25_DS_003
2024-25_DS_004
2024-25_DS_005
2024-25_DS_006
2024-25_DS_007
2024-25_DS_008
2024-25_DS_009
2024-25_DS_010
2024-25_DS_011
2024-25_DS_012

2024-25_DS_013

2024-25_DS_014
Project ID
2024-25_DS_015
2024-25_DS_016
2024-25_DS_017
2024-25_DS_018
2024-25_DS_019
2024-25_DS_020
2024-25_DS_021
2024-25_DS_022
2024-25_DS_023
2024-25_DS_024
2024-25_DS_025
2024-25_DS_026
2024-25_DS_027
2024-25_DS_028
2024-25_DS_029
Title
Deep Ensemble Learning With Pruning for DDoS Attack Detection in IoT Networks
Classifying Routine Clinical Electroencephalograms With Multivariate Iterative Filtering and Convolutional Neural Networks
Exploring COVID-19 Trends in Mexico During the Winter Season with Explainable Artificial Intelligence (XAI)
Applying Competition-Based Learning to Stimulate Students’ Practical and Competitive AI Ability in a Machine Learning Cur
Traffic Data-Empowered XGBoost-LSTM Framework for Infectious Disease Prediction
A deep multimodal fusion and multitasking trajectory prediction model for typhoon trajectory prediction to reduce flight sched
Achieving Multi-Time-Step Segment Routing via Traffic Prediction and Compressive Sensing Techniques
Long-Term Prediction of Sea Surface Temperature by Temporal Embedding Transformer With Attention Distilling and Partial
Artificial Intelligence and Machine Learning for Improving Glycemic Control in Diabetes: Best Practices, Pitfalls, and Opportu
EMG-based Multi-User Hand Gesture Classification via Unsupervised Transfer Learning Using Unknown Calibration Gestures
Indirect Estimation of Breathing Rate Using Wearable Devices
Advances and Challenges in Meta-Learning: A Technical Review

A Multi-Modal Classification Method for Early Diagnosis of Mild Cognitive Impairment and Alzheimer’s Disease Using Thre

Digital Twinning of Cardiac Electrophysiology Models From the Surface ECG: A Geodesic Backpropagation Approach
Title
Deep Learning for Radio Resource Allocation Under DoS Attack
Incremental Adversarial Learning for Polymorphic Attack Detection
Gender-Based Analysis of User Reactions to Facebook Posts
Deep Learning-Based Assessment Model for Real-Time Identification of Visual Learners Using Raw EEG
An Improved Extreme Learning Machine (ELM) Algorithm for Intent Recognition of Transfemoral Amputees with Powered K
Analysis of Cancer-associated Mutations of POLB using Machine Learning and Bioinformatics
BIOWISH: Biometric Recognition Using Wearable Inertial Sensors Detecting Heart Activity
Bad and Good Errors: Value-Weighted Skill Scores in Deep Ensemble Learning
Classification of Tolerances in Permanent Magnet Synchronous Machines With Machine Learning
A Cost-Sensitive Machine Learning Model With Multitask Learning for Intrusion Detection in IoT
An IoMT-Based Incremental Learning Framework With a Novel Feature Selection Algorithm for Intelligent Diagnosis in Smar
Applying Competition-Based Learning to Stimulate Students’ Practical and Competitive AI Ability in a Machine Learning Cur
Exploring Classification of Topological Priors With Machine Learning for Feature Extraction
Multilayer Perceptron Neural Network Approach to Classifying Learning Modalities Under the New Normal
E-Commerce_Fraud_Detection_Based_on_Machine_Learning_Techniques_Systematic_Literature_Review
 Domain
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science

Data Science

Data Science
Domain
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Data Science
Project ID

2024-25_AI_001

2024-25_AI_002

2024-25_AI_003

2024-25_AI_004

2024-25_AI_005

2024-25_AI_006

2024-25_AI_007

2024-25_AI_008

2024-25_AI_009

2024-25_AI_010

2024-25_AI_011

2024-25_AI_012

Project ID

2024-25_AI_013

2024-25_AI_014

2024-25_AI_015

2024-25_AI_016

2024-25_AI_017

2024-25_AI_018

2024-25_AI_019

2024-25_AI_020

2024-25_AI_021

2024-25_AI_022

2024-25_AI_023

2024-25_AI_024

2024-25_AI_025
Title

A Real Time Span Data Recognizer System using AI Technology

A Semantic Assist : Guidance Chatbot System

An efficient Recommendation of User Whishlist using AI

Smart Finder : A spam detection method in messages using AI

Elegant Twin Face Analyzer using AI

Control Me : Voice Assistance for System Controls

Digit Recognition Using AI

A Prior Forecasting of Stock Market Range using Ai method in recent trends

Place of Customer : Ai Based customer satisfaction monitoring system

AI based prediction of Harsh conversation between people

A Collaborative AI and ML technique to predict good quality product and recommend to user

AI-powered diagnostics and personalized medicine enhance patient care

Title

Ai Based Speech Practice System

Engages with real-world E-Learning to enhance learning outcomes.

Advance AI based Robot Navigation in MAZE detection

Ai enhanced Marketing and Sales Analytics for future prediction

AI face Enhancer

AI Driven Battery Management and optimization technique

Spam Email Detector using Artificial Intelligence

Real-time Translation Tool

Sentiment Analysis of Social Media Using Artificial Intelligence

Application of translation technology based on AI in translation teaching

Artificial Intelligence Based Language Translation Platform

Artificial Intelligence Based Customer Churn Prediction Model for Business Market

Use of explainable AI to interpret the results of NLP models for sentimental analysis
 Domain

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Domain

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence

Artificial Intelligence
Project ID
2024-25_CLD_001

2024-25_CLD_002

2024-25_CLD_003

2024-25_CLD_004

2024-25_CLD_005

2024-25_CLD_006

2024-25_CLD_007

2024-25_CLD_008

2024-25_CLD_009

2024-25_CLD_010

2024-25_CLD_011

2024-25_CLD_012

2024-25_CLD_013

2024-25_CLD_014

2024-25_CLD_015

Project ID

2024-25_CLD_016

2024-25_CLD_017

2024-25_CLD_018

2024-25_CLD_019

2024-25_CLD_020

2024-25_CLD_021

2024-25_CLD_022
2024-25_CLD_023

2024-25_CLD_024

2024-25_CLD_025

2024-25_CLD_026

2024-25_CLD_027

2024-25_CLD_028

2024-25_CLD_029
2024-25_CLD_030
Title
Multi-Dimensional Flat Indexing for Encrypted Data

Automating VPN Configuration in Computer Networks

Quantized Distributed Economic Dispatch for Microgrids: Paillier Encryption-Decryption Scheme

Joint Task Offloading, Resource Allocation, and Trajectory Design for Multi-UAV
Cooperative Edge Computing with Task Priority
Hybrid Optimization Algorithm for Detection ofSecurity Attacks in IoT-Enabled CyberPhysical Systems

Towards Safe Load Balancing based on Control Barrier Functions and Deep Reinforcement Learning
LESSON: Multi-Label Adversarial False Data Injection Attack for Deep Learning Locational
Detection
HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning

DiffMDD: A Diffusion-Based Deep LearningFramework for MDD Diagnosis Using EEG

On the Privacy Effect of Data Enhancement via the Lens of Memorization

Towards Automated Attack Discovery in SDN Controllers Through Formal Verification

Federated-Reinforcement Learning-Assisted IoT Consumers System for Kidney Disease Images

Multi-agent Reinforcement Learning based Distributed Channel Access for Industrial
Edge-Cloud Web 3.0
Application of Machine LearningOptimizationinCloud Computing Resource SchedulingandManagement
Multi Objective Prioritized Workflow Scheduling Using Deep Reinforcement Based Learning
in Cloud Computin
Title

Security for the Metaverse: Blockchain and Machine Learning Techniques for Intrusion Detection

Defending Against Poisoning Attacks in Federated Learning with Blockchain

User Connection and Resource Allocation Optimization in Blockchain Empowered Metaverse over 6G Wireless
Communications

A User Based HVAC System Management Through Blockchain Technology and Model Predictive Control

Enhancing Cloud Computing Security with Fast, Secure, and Anonymous Key Agreement: Overcoming Bad
Randomness for Improved Privacy

ProSecutor: Protecting Mobile AIGC Services on Two-Layer Blockchain via Reputation and Contract Theoretic
Approaches

Electronic Voting Using Block chain Technology

BIONIB: Blockchain-based IoT using Novelty Index in Bridge Health Monitoring

Blockchain-assisted Lightweight Authenticated Key Agreement Security Framework for Smart Vehicles-enabled
Intelligent Transportation System

S-MBDA: A Blockchain-based Architecture for Secure Storage and Sharing of Material Big-Data

SC-CAAC: A Smart-Contract-Based Context-Aware Access Control Scheme for Blockchain-Enabled IoT Systems

CRPWarner: Warning the Risk of Contract-related Rug Pull in DeFi Smart Contracts

ISCSCLV: Improving Smart Contract Security with Contrastive Learning-based Vulnerability Detection

Collaborative Learning for Cyberattack Detection in Blockchain Networks

Secure and Efficient Federated Learning Through Layering and Sharding Blockchain
 Domain
Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Domain

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing
Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing

Cloud Computing
Cloud Computing
Project ID Title
Asymmetric SVPWM and Error Suppression Method for Current
2024-25_PE_001
Reconstruction of T-type Three-Level Inverter

2024-25_PE_002 An Energy-Based Model of Four-Switch Buck–Boost Converters

A Review of Broadband Frequency Techniques for Insulation Monitoring

2024-25_PE_003
and Diagnosis in Rotating Electrical Machines
Optimized 9-Level Switched-Capacitor Inverter for Grid-Connected
2024-25_PE_004
Photovoltaic System

2024-25_PE_005 Virtual Synchronous Machine Control for Asynchronous Grid Connections

Reconfiguration of Bipolar HVDC System for Continuous Transmission

2024-25_PE_006
Under DC Line Fault
30 kW Bidirectional Inductive Power Transfer Charger With Intermediate
2024-25_PE_007
Coil for EV Applications

Multi-scale Fusion Model Based on Gated Recurrent Unit for Enhancing

2024-25_PE_008
Prediction Accuracy of State-of-charge in Battery Energy Storage Systems

A Novel Hermite Interpolation-Based MPPT Technique for Photovoltaic

2024-25_PE_009
Systems Under Partial Shading Conditions
Over 98% Efficiency SiC-MOSFET based Four-Phase Interleaved
2024-25_PE_010
Bidirectional DC-DC Converter Featuring Wide-Range Voltage Ratio
High-efficiency Modulation Scheme for Three-Level Buck Four-Leg
2024-25_PE_011
Current-Source Inverter

A Soft-switched Multi-port Converter for PV/Supercapacitors Hybrid

2024-25_PE_012
Systems enabling Frequency Response Services

A Wireless Self-Powered I-V Curve Tracer for On-Line Characterization of

2024-25_PE_013
Individual PV Panels

Project ID Title

Centralised Multimode Power Oscillation Damping Controller for

2024-25_PE_014
Photovoltaic Plants With Communication Delay Compensation

DecentralizedDynamicPowerSharingControlforFrequencyRegulationUsingH
2024-25_PE_015
ybridHydrogenElectrolyzerSystems

Deep Learning-Based Models for Predicting Poorly Damped Low-Frequency

2024-25_PE_016
Modes of Oscillations

Gain and Phase: Decentralized Stability Conditions for Power Electronics-

2024-25_PE_017
Dominated Power Systems

Reclosers Modeling for Temporal Simulation of Distribution Networks in

2024-25_PE_018
Simulink/Matlab
 Fast and Accurate Non-linear Model for Synchronous Machines Including
2024-25_PE_019
Core Losses

On the Analysis and Synthesis of Wind Turbine Side–Side Tower Load

2024-25_PE_020
Control via Demodulation

Impact of DC-Link Voltage Control on Torsional Vibrations in Grid-Forming

2024-25_PE_021
PMSG Wind Turbines

General and Unified Model of the Power Flow Problem in Multiterminal

2024-25_PE_022
AC/DC Networks

Predicting DC-Link Capacitor Current Ripple in AC-DC Rectifier Circuits

2024-25_PE_023
Using Fine-Tuned Large Language Models

Capacitor Voltage Balancing Method for the Hybrid Multilevel Converter

2024-25_PE_024
Considering Grid Voltage Sags

Space Vector Modulation With Common-Mode Voltage Elimination and

2024-25_PE_025
Switching Frequency Minimization for Multilevel Converters

Progress in artificial intelligence applicationsbasedon the combination of

2024-25_PE_026
self-driven sensorsanddeeplearning

Project ID Title

Effective Application of IoT Power Electronics Technology and Power

2024-25_PE_027
System Optimization Control
Efficient and Fast Wind Turbine MPPT Algorithm Using TS Fuzzy Logic
2024-25_PE_028
and Optimal Relation Methods
Genetic Algorithm-Based Optimal Sizing of Hybrid Battery/Ultracapacitor
2024-25_PE_029
Energy Storage System for Wave Energy Harvesting Applications
Multi-Micro Grid System Reinforcement Across Deregulated Markets,
2024-25_PE_030 Energy Resources Scheduling and Demand Side Management Using a
MultiAgent-Based Optimization in Smart Grid Paradigm
Passivity and Decentralized Stability Conditions for Grid-Forming
2024-25_PE_031
Converters
Quantitative Stability Conditions for Grid-Forming Converters With
2024-25_PE_032
Complex Droop Control
Advancing Electric Vehicle Charging Ecosystems with Intelligent Control of
2024-25_PE_033
DC Microgrid Stability
Distributed Control of Islanded DC Microgrids: A Passivity-Based Game
2024-25_PE_034
Theoretical Approach
A Coordinated Multitimescale Model Predictive Control for Output Power
2024-25_PE_035
Smoothing in Hybrid Microgrid Incorporating Hydrogen Energy Storage
PowerFlowMultiNet: Multigraph Neural Networks for Unbalanced Three-
2024-25_PE_036
Phase Distribution Systems

2024-25_PE_037 FaultSSL: Seismic Fault Detection via Semi-supervised learning

 Convex Optimal Power Flow Based on Power Injection-based Equations and
2024-25_PE_038
Its Application in Bipolar DC Distribution Network
PowerFlowMultiNet: Multigraph Neural Networks for Unbalanced Three-
2024-25_PE_039
Phase Distribution Systems
 Domain

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Domain

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics
Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Domain

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics

Power Electronics
Power Electronics

Power Electronics
S.No Domain

1 Artificial Intelligence

2 Artificial Intelligence

3 Artificial Intelligence

4 Artificial Intelligence

5 Artificial Intelligence

6 Artificial Intelligence

7 Artificial Intelligence

8 Artificial Intelligence

9 Artificial Intelligence
10 Artificial Intelligence

11 Artificial Intelligence

12 Artificial Intelligence

13 Artificial Intelligence

14 Artificial Intelligence

15 Artificial Intelligence

16 Artificial Intelligence

17 Artificial Intelligence

18 Artificial Intelligence

19 Artificial Intelligence

20 Artificial Intelligence

21 Artificial Intelligence
22 Artificial Intelligence

23 Artificial Intelligence

24 Artificial Intelligence

25 Artificial Intelligence

26 Artificial Intelligence

27 Artificial Intelligence

28 Application

29 Application

30 Application

31 Application

32 Application

33 Application
34 Application

35 Application

36 Application

37 Application

38 Application

39 Application

40 Application

41 Application

42 Application

43 Application

44 Application

45 Application

46 Application

47 Application

48 Application
49 Application

50 Application

51 Application

52 Application

53 Application

54 Application

55 Application

56 Application

57 Application

58 Application

59 Application

60 Application

61 Application

62 Application

63 Application

64 Application
65 Application

66 Application

67 Application

68 Application

69 Application

70 Application

71 Application

72 Application

73 Application

74 Application

75 Application

76 Application

77 Application

78 Application

79 Application

80 Application
81 Application

82 Application

83 Application

84 Application

85 Application

86 Application

87 Application

88 Application

89 Application

90 Application

91 Application

92 Application

93 Application

94 Application
 95 Application

96 Application

97 Application

98 Application

99 Application

100 Application

101 Application

102 Application

103 Application

104 Application

105 Application

106 Application

107 Application
108 Application

109 Application

110 Application

111 Application

112 Application

113 Application

114 Application

115 Application

116 Application

117 Application

118 Application

119 Application

120 Application

121 Application

122 Application

123 Application
124 Application

125 Application

126 Application

127 Application

128 Application

129 Application

130 Application

131 Application

132 Application

133 Application

134 Application

135 Application

136 Application

137 Application

138 Application

139 Application
140 Application

141 Application

142 Application

143 Application

144 Application

145 Application

146 Application

147 Application

148 Application

149 Application

150 Application

151 Application

152 Application

153 Application

154 Application

155 Application

156 Application

157 Application
158 Application

159 Application

160 Application

161 Application

162 Application

163 Application

164 Application

165 Application

166 Application

167 Application

168 Application

169 Application

170 Application

171 Application

172 Application

173 Application

174 Application

175 Application
176 Application

177 Application

178 Application

179 Application

180 Application

181 Application

182 Application

183 Application

184 Application

185 Application

186 Application

187 Application

188 Application

189 Application

190 Application

191 Application

192 Application
193 Blockchain

194 Blockchain

195 Blockchain

196 Blockchain

197 Blockchain

198 Blockchain
199 Blockchain

200 Blockchain

201 Blockchain

202 Blockchain

203 Blockchain

204 Blockchain

205 Blockchain
206 Blockchain

207 Blockchain

208 Blockchain

209 Blockchain

210 Blockchain

211 Blockchain

212 Blockchain

213 Cloud Computing

214 Cloud Computing

215 Cloud Computing

216 Cloud Computing

217 Cloud Computing

218 Cloud Computing

219 Cloud Computing

220 Cloud Computing

221 Cloud Computing

222 Cloud Computing

223 Cloud Computing

224 Cloud Computing

225 Cloud Computing

226 Cloud Computing

227 Wireless Communication

228 Wireless Communication

229 Wireless Communication

230 Wireless Communication

231 Wireless Communication

232 Wireless Communication

233 Wireless Communication

234 Wireless Communication

235 Wireless Communication

236 Wireless Communication

237 Wireless Communication

238 Cybersecurity
239 Cybersecurity

240 Cybersecurity

241 Cybersecurity

242 Cybersecurity
243 Cybersecurity

244 Cybersecurity

245 Cybersecurity

246 Cybersecurity

247 Cybersecurity

248 Cybersecurity
249 Cybersecurity

250 Cybersecurity

251 Cybersecurity

252 Cybersecurity

253 Cybersecurity

254 Cybersecurity

255 Cybersecurity
256 Cybersecurity

257 Cybersecurity

258 Cybersecurity

259 Cybersecurity

260 Cybersecurity

261 Cybersecurity

262 Cybersecurity

263 Cybersecurity

264 Cybersecurity
265 Cybersecurity

266 Cybersecurity

267 Cybersecurity

268 Cybersecurity

269 Cybersecurity

270 Cybersecurity

271 Cybersecurity

272 Cybersecurity

273 Cybersecurity
274 Cybersecurity

275 Cybersecurity

276 Cybersecurity

277 Cybersecurity

278 Cybersecurity

279 Cybersecurity

280 Cybersecurity

281 Cybersecurity

282 Cybersecurity

283 Cybersecurity

284 Cybersecurity

285 Cybersecurity
286 Cybersecurity

287 Cybersecurity

288 Cybersecurity

289 Cybersecurity

290 Cybersecurity

291 Cybersecurity

292 Cybersecurity

293 Cybersecurity

294 Cybersecurity
295 Cybersecurity

296 Cybersecurity

297 Cybersecurity

298 Cybersecurity

299 Cybersecurity

300 Cybersecurity

301 Cybersecurity

302 Cybersecurity

303 Data Mining

304 Data Mining

305 Data Mining

306 Data Mining

307 Data Mining

308 Data Mining

309 Data Mining

310 Data Mining

311 Data Mining

312 Data Mining

313 Data Mining

314 Data Mining

315 Data Mining

316 Data Mining

317 Data Mining

318 Data Mining

319 Data Mining

320 Data Mining

321 Data Mining

322 Data Mining

323 Data Mining

324 Data Mining

325 Data Mining

326 Data Mining

327 Data Mining

328 Data Mining

329 Data Mining

330 Data Mining

331 Data Mining

332 Data Mining

333 Data Mining

334 Data Mining

335 Data Mining

336 Data Mining

337 Data Mining

338 Data Mining

339 Data Mining

340 Data Mining

341 Data Mining

342 Data Mining

343 Data Mining

344 Data Mining

345 Data Mining

346 Data Mining

347 Data Mining

348 Data Mining

349 Data Mining

350 Data Mining

351 Data Mining

352 Data Mining

353 Data Mining

354 Data Mining

355 Data Mining

356 Data Mining

357 Data Mining

358 Data Mining

359 Data Mining

360 Data Mining

361 Data Mining

362 Data Mining

363 Data Mining

364 Data Mining

365 Data Mining

366 Data Mining

367 Data Mining

368 Data Mining

369 Data Mining

370 Data Mining

371 Deep Learning

372 Deep Learning

373 Deep Learning

374 Deep Learning

375 Deep Learning

376 Deep Learning

377 Deep Learning

378 Deep Learning

379 Deep Learning

380 Python Web Application Django

381 Python Web Application Django

382 Python Web Application Django

383 Python Web Application Django

384 Python Web Application Django

385 Python Web Application Django

386 Python Web Application Django

387 Python Web Application Django

388 Python Web Application Django

389 Python Web Application Django

390 Python Web Application Django

391 Python Web Application Django

392 Python Web Application Django

393 Python Web Application Django

394 Python Web Application Django

395 Python Web Application Django

396 Python Web Application Django

397 Python Web Application Django

398 Python Web Application Django

399 Python Web Application Django

400 Python Web Application Django

401 Python Web Application Django

402 Python Web Application Django

403 Python Web Application Django

404 Python Web Application Django

405 Python Web Application Django

406 Python Web Application Django

407 Python Web Application Django

408 Python Web Application Django

409 Python Web Application Django

410 Python Web Application Django

411 Python Web Application Django

412 Python Web Application Django

413 Python Web Application Django

414 Python Web Application Django

415 Python Web Application Django

416 Python Web Application Django

417 Python Web Application Django

418 Python Web Application Django

419 Python Web Application Django

420 Python Web Application Django

421 Python Web Application Django

422 Python Web Application Django

423 Python Web Application Django

424 Image Processing

425 Image Processing
426 Image Processing

427 Image Processing

428 Image Processing

429 Image Processing

430 Image Processing

431 Image Processing

432 Image Processing

433 Image Processing

434 Image Processing

435 Image Processing

436 Image Processing

437 Image Processing

438 Image Processing

439 Image Processing

440 Image Processing

441 Image Processing

442 Image Processing

443 Image Processing

444 Image Processing

445 Image Processing

446 Image Processing

447 Image Processing

448 Image Processing

449 Image Processing

450 Image Processing

451 Image Processing

452 Image Processing

453 Image Processing

454 Image Processing

455 Image Processing

456 Image Processing

457 Image Processing

458 Image Processing

459 Image Processing

460 Image Processing

461 Image Processing

462 Image Processing

463 Image Processing

464 Image Processing

465 Image Processing

466 Image Processing

467 Image Processing

468 Image Processing

469 Image Processing

470 Image Processing

471 Image Processing

472 Image Processing

473 Image Processing

474 Power Electronics

475 JAVA JSP Web Application

476 JAVA JSP Web Application

477 JAVA JSP Web Application

478 JAVA JSP Web Application

479 JAVA JSP Web Application

480 JAVA JSP Web Application

481 JAVA JSP Web Application

482 JAVA JSP Web Application

483 JAVA JSP Web Application

484 JAVA JSP Web Application

485 Machine Learning

486 Machine Learning

487 Machine Learning

488 Machine Learning

489 Machine Learning

490 Machine Learning

491 Machine Learning

492 Machine Learning

493 Machine Learning

494 Machine Learning

495 Machine Learning

496 Machine Learning

497 Machine Learning

498 Machine Learning

499 Machine Learning

500 Machine Learning

501 Machine Learning

502 Machine Learning

503 Machine Learning

504 Machine Learning

505 Machine Learning

506 Machine Learning

507 Machine Learning

508 Machine Learning

509 Machine Learning

510 Machine Learning

511 Machine Learning

512 Machine Learning

513 Machine Learning

514 Machine Learning

515 Machine Learning

516 Machine Learning

517 Wireless Communication

518 Wireless Communication

519 Wireless Communication

520 Wireless Communication

521 Application

522 Power Electronics

523 Power Electronics

524 Power Electronics

525 Power Electronics

526 Power Electronics

527 Power Electronics

528 Power Electronics

529 Power Electronics

530 Power Electronics

531 Power Electronics

532 Power Electronics

533 Power Electronics

534 Power Electronics

535 Power Electronics

536 Power Electronics

537 Power Electronics

538 Power Electronics

539 Power Electronics

540 Power Electronics

541 Power Electronics

542 Power Electronics

543 Power Electronics

544 Power Electronics

545 Power Electronics

546 Power Electronics

547 Power Electronics

548 Power Electronics

549 Power System

550 Power System

551 Power System

552 Power System

553 Power System

554 Power System

555 Power System

556 Power System

557 Power System

558 Power System

559 Power System

560 Signal Processing

561 Signal Processing

562 Signal Processing

563 Machine Learning

564 Machine Learning

565 Machine Learning

566 Machine Learning

567 Machine Learning

568 Machine Learning

569 Machine Learning

570 VLSI

571 VLSI

572 VLSI

573 VLSI
574 VLSI

575 VLSI

576 VLSI
577 VLSI

578 VLSI

579 VLSI

580 VLSI

581 Wireless Communication

582 Wireless Communication

583 Wireless Communication

584 Wireless Communication

585 Wireless Communication

586 Wireless Communication

587 Wireless Communication

588 Wireless Communication

589 Wireless Communication

590 Wireless Communication

591 Wireless Communication

592 Wireless Communication

593 Wireless Communication

594 Wireless Communication

595 Wireless Communication

596 Wireless Communication

597 Wireless Communication

598 Wireless Communication

599 Wireless Communication

600 Wireless Communication

601 Wireless Communication

602 Wireless Communication

603 Wireless Communication

604 Wireless Communication

605 Wireless Communication

606 Wireless Communication

607 Wireless Communication

608 Wireless Communication

609 Wireless Communication

610 Wireless Communication

611 Wireless Communication

612 Wireless Communication

613 Wireless Communication

614 Wireless Communication

615 Wireless Communication

616 Wireless Communication
Title

Mood Swing Analysis using Artificial Intelligence

Artificial Intelligence assisted Stock Management System

A Real Time Span Data Recognizer System using AI Technology

A Semantic Assist : Guidance Chatbot System

An efficient Recommendation of User Whishlist using AI

Smart Finder : A spam detection method in messages using AI

Elegant Twin Face Analyzer using AI

Control Me : Voice Assistance for System Controls

Digit Recognition Using AI

A Prior Forecasting of Stock Market Range using Ai method in
recent trends

Place of Customer : Ai Based customer satisfaction monitoring

system

AI based prediction of Harsh conversation between people

A Collaborative AI and ML technique to predict good quality

product and recommend to user

AI-powered diagnostics and personalized medicine enhance

patient care

Ai Based Speech Practice System

Engages with real-world E-Learning to enhance learning

outcomes.

Advance AI based Robot Navigation in MAZE detection

Ai enhanced Marketing and Sales Analytics for future prediction

AI face Enhancer

AI Driven Battery Management and optimization technique

Spam Email Detector using Artificial Intelligence

Real-time Translation Tool

Sentiment Analysis of Social Media Using Artificial Intelligence

Application of translation technology based on AI in translation

teaching

Artificial Intelligence Based Language Translation Platform

Artificial Intelligence Based Customer Churn Prediction Model

for Business Market

Use of explainable AI to interpret the results of NLP models for

sentimental analysis

Bid Bazaar using Django

Advanced Commercial Entities for Business Registry System

Fine-Tuning Financial Process for Enhancing Financial Workflow

Efficiency

Swiftly booking - Odyssey Planner website using Node JS

A real time application for Developer Symphony From Blogs

Using Node JS

Elevating Store Operations and management to the Cosmos using

Node JS and MySQL
E-commerce Experience on Online Shopping platforms Using
Node JS and MySQL

Med Optima for Futuristic Pharmacy operational Suite using

Node JS

Next-Gen Automotive Sales Platform with interactive UI by

React.

AI based Sentient Forge with Emotional Intelligence Solutions

for Decision-Makers

Real-time Chat Application using Node.js

Calendar -schedule Management-System

Weather Dashboard with Node.js and API Integration

Job Portal with Node.js and Express

Inventory management system using node JS

Expense Tracker with Node.js and Chart Visualization

Node.js-based Employee Management System

Real-time Polling Application with Node.js

Node.js-based Restaurant Ordering System

Online Quiz Application using Node.js

Node.js-based Personal Journaling App

Node.js-based Employee Feedback System

Node.js-based Content Management System (CMS)

Online Learning Platform with Node.js

ERP MODEL FOR COOKED SUPPLY CHAIN

Car Accessories Marketplace

E-commerce Experience on Online Shopping platforms Using

Node JS and Mongo DB

Paint website using angular and JSON data

News web Application using Node JS

Bookstore Library management

Media streaming application

Company Visitor management system

Online gas booking System

Notes management system

Online FIR management system

Faculty profile management system

Social media web application

Cinema reservation system

Matrimonial system using Node JS

E-Pass management system

Stackoverflow clone- mui React

Grocery suggestion web application

Smart Car Parking System in MERN stack

Ecommerce with POS Inventory in MERN Stack

garbage collection system in Node Js

Complaint Submission Using Block Chain

Gmail-Imap -application

Vaccine suplay Chain using Block chain

Human resource mangemnet System

Online Auction Application

Cargo Management System

Automated College Timetable

Career Guidance AI Chatbot

Disaster Alert and Crisis Relife

Farmer Harvest Connect: A MERN Stack Platform for Hiring

Vehicles, Manpower,and Selling Crops

Payroll Management System React JS

Nutrient Recommendation MERN Stack

Event Marriage Hall Booking using MERN React JS

Online Driver Hiring Using MERN Stack

Disaster Alert and Crisis Relife Response Coordination platfrom

Using MERN Stack React JS

Food Recipe Recommendation system using MERN Stack Web

application

Lost & Found Finder Using MERN Application

PG Finder And Hostel Booking Management Using MERN React

JS

Online PocSo Child Complaint Management system using MERN

Stack Web application

Training Driving School Management System Using MERN

Stack

Women Legal Aid Advocate Finder App

Organ Donation Management App

Electric Vehicle Charging Station Locator

eAyurvedic Comprehensive Disease Solutions

Smart Business Platform: Retailer, Distributor, Stockist

Child Safety Protection Application

PG Locator: Find Hostels or Rental Houses

eLearning Platform: Skill Development and Education

Ambulance and Police Emergency Application

Health and Diet Management App

Rescue Wings: Disaster Response App

Digital Vehicle Management System

Bike and Car Service Management System

Agro App: Government-Aided Farmer Schemes

Employee Leave Tracking System

Student Assistance Chatbot

Doctor-Patient Portal in Core PHP

Clothing Recommendation System

Automated Timetable Creation System

Social Networking Website Platform

Online Voting System

Product Rating System Based on Consumer Reviews

Online Cake Ordering Platform

Inventory Management System

Social Networking Platform Similar to Facebook

Online Wedding Planning Service

Daily Expense Tracking System

Library Management System

Online Birth Certificate Registration System

Online GST Billing Solution

Online Sports Equipment Store

Zoo Management System

Alumni Network Management System

Online Pharmaceutical Sales Platform

Online Bakery Management System

Online Food Delivery System

Company Visitor Tracking System

E-Pass Issuance System

Airline Reservation System

Online Matrimonial Service

Banking Management System in PHP

Online Gas Booking System

Tuition Communication Portal in PHP and MySQL

Minimal News Content Management System in PHP

Rescue Pet Adoption Platform

Event Management System for College Fests

Online Music Streaming Player

Online Course Registration System

Doctor Appointment Scheduling System

Laundry Services Management System

Simple Task Management Web Application

Quiz Application Development

University Admission Online Process

Advanced Online Courier Booking System

Pizza Ordering and Ingredient Input System

Chat Application Developed with PHP and MySQL

Attendance Management System with Movie Theater Layout

Online Railway Ticket Reservation System

Multilingual Course Content Management System

Question Paper Generation Application

Phone Repair Tracking System in PHP and MySQL

Mentor Allocation System

Notes Management System

Student Cleaning Service Scheduling Application

Social Media Platform (Social Spark) Using Core PHP

Art Gallery Management System

Online Polling System in PHP

Online Bus Ticket Reservation System

Online Notice Board System

Farm Management System

Online Musical Instrument Store in PHP

Jewelry Shop Management System in PHP

Matrimonial Service Management in PHP

Interview Management System in PHP

Hotel and Tourism Booking System in PHP

Smart Parking Management System in PHP

Insurance Management System

Cinema Seat Booking System in PHP

Invoicing System in PHP

Responsive Blog Platform in PHP

Traffic Violation Reporting System

Patient Record Management System

Campus Recruitment Management System

Sports Event Management Platform

Faculty Profile Management System

Social Media Application Similar to Facebook

Dynamic Portfolio Website in PHP

Public Complaints Portal in PHP

CRM System Enhanced with Sentiment Analysis in PHP

Gym and Fitness Club Management System in PHP

Online Blood Bank Management System in PHP

Lab Report Management System in PHP

Driving School Management System in PHP

Automated Loan Verification System in PHP

Automated Faculty Evaluation Platform in PHP

Operational Schedule Management System in PHP

EliteSalon: Comprehensive Management System

EcoCharge Hub: Advanced Electric Vehicle Charging Station

StudentSuccess: Advanced College Results Management System

StudentSeminarPro: Advanced Hall Booking System

Security for the Metaverse: Blockchain and Machine Learning
Techniques for Intrusion Detection

Defending Against Poisoning Attacks in Federated Learning with

Blockchain

User Connection and Resource Allocation Optimization in

Blockchain Empowered Metaverse
over 6G Wireless Communications

A User Based HVAC System Management Through Blockchain

Technology and Model
Predictive Control

Enhancing Cloud Computing Security with Fast, Secure, and

Anonymous Key Agreement:
Overcoming Bad Randomness for Improved Privacy

ProSecutor: Protecting Mobile AIGC Services on Two-Layer

Blockchain via Reputation and
Contract Theoretic Approaches
Electronic Voting Using Block chain Technology

BIONIB: Blockchain-based IoT using Novelty Index in Bridge

Health Monitoring

Blockchain-assisted Lightweight Authenticated Key Agreement

Security Framework for Smart
Vehicles-enabled Intelligent Transportation System

S-MBDA: A Blockchain-based Architecture for Secure Storage

and Sharing of Material Big-Data

SC-CAAC: A Smart-Contract-Based Context-Aware Access

Control Scheme for Blockchain-Enabled
IoT Systems

CRPWarner: Warning the Risk of Contract-related Rug Pull in

DeFi Smart
Contracts

ISCSCLV: Improving Smart Contract Security with Contrastive

Learning-based Vulnerability Detection
Collaborative Learning for Cyberattack Detection in Blockchain
Networks

Secure and Efficient Federated Learning Through Layering and

Sharding Blockchain

Safeguarding Patient Data-Sharing: Blockchain-Enabled

Federated Learning in Medical
Diagnostics

PPBFL: A Privacy Protected Blockchain-based Federated

Learning Model

zkFL: Zero-Knowledge Proof-based Gradient Aggregation for

Federated Learning

Federated Learning Meets Blockchain in Decentralized Data

Sharing: Healthcare Use Case

Distributed IIoT Anomaly Detection Scheme Based on

Blockchain and Federated Learning

Multi-Dimensional Flat Indexing for Encrypted Data

Automating VPN Configuration in Computer Networks

Quantized Distributed Economic Dispatch for Microgrids: Paillier
Encryption-Decryption Scheme

Joint Task Offloading, Resource Allocation, and Trajectory

Design for Multi-UAV
Cooperative Edge Computing with Task Priority

Hybrid Optimization Algorithm for Detection ofSecurity Attacks

in IoT-Enabled CyberPhysical Systems

Towards Safe Load Balancing based on Control Barrier Functions

and Deep Reinforcement Learning

HashVFL: Defending Against Data Reconstruction Attacks in

Vertical Federated Learning

DiffMDD: A Diffusion-Based Deep LearningFramework for

MDD Diagnosis Using EEG

On the Privacy Effect of Data Enhancement via the Lens of

Memorization

Towards Automated Attack Discovery in SDN Controllers

Through Formal Verification
Federated-Reinforcement Learning-Assisted IoT Consumers
System for Kidney Disease Images

Multi-agent Reinforcement Learning based Distributed Channel

Access for Industrial
Edge-Cloud Web 3.0

Application of Machine LearningOptimizationinCloud

Computing Resource SchedulingandManagement

Multi Objective Prioritized Workflow Scheduling Using Deep

Reinforcement Based Learning
in Cloud Computin

AoI-aware Sensing Scheduling and Trajectory Optimization for

Multi-UAV-assisted Wireless Backscatter Networks

AR-RIS-Assisted Communication Radar Coexistence: Analysis

and Optimization

Attacking and Defending Deep-Learning-Based Off-Device

Wireless Positioning Systems

Generalized Automatic Modulation Classification for OFDM

Systems Under Unseen Synthetic Channels
A Meta-DDPG Algorithm for Energy and Spectral Efficiency
Optimization in STAR-RIS-Aided SWIPT

Networked Integrated Sensing and Communications for 6G

Wireless Systems

Frequency-Selective Adversarial Attack Against Deep Learning-

Based Wireless Signal Classifiers

Experimental Demostration of a MIMO-OFDM Underwater

Optical Communication System

Optimized Routing Protocol Through Exploitation of Trajectory

Knowledge for UAV Swarms

Joint Visibility Region and Channel Estimation for Extremely

Large-Scale MIMO Systems

A Novel Local and Hyper-Local Multicast Services

Transmission Scheme for Beyond 5G Networks

An Unsupervised Adversarial Autoencoder for Cyber Attack

Detection in Power Distribution Grids
Classification and Characterization of Encoded Traffic in
SCADA Network using Hybrid Deep Learning Scheme

An Intelligent Big Data Security Framework Based on AEFS-

KENN Algorithms for the Detection of Cyber-Attacks from
Smart Grid Systems

A Monolithic Cybersecurity Architecture for Power Electronic

Systems

Utilizing Deep Learning for Enhancing Network Resilience in

Finance
Applying Large Language Models to PowerSystems: Potential
Security Threats

Multi-phase Quantum resistant Framework for Secure

Communication in SCADA Systems

The Role of Deep Learning in Advancing Proactive Cybersecurity

Measures for Smart Grid Networks

Modeling and Assessment of Cyber Attacks Targeting Converter-

Driven Stability of Power Grids
With PMSG-Based Wind Farms

Resource-Constraint Deep Forest based Intrusion Detection

Method in Internet of Things for
Consumer Electronic

ECF-IDS: An Enhanced Cuckoo Filter-based Intrusion Detection

System for In-vehicle Network
Advancing DDoS Attack Detection: A Synergistic Approach
Using Deep Residual
Neural Networks and Synthetic Oversampling

Advancing DDoS Attack Detection: A Synergistic Approach

Using Deep Residual
Neural Networks and Synthetic Oversampling

Defending Against Poisoning Attacks in Federated Learning with

Blockchain

PEAE-GNN: Phishing Detection on Ethereum via Augmentation

Ego-Graph Based on
Graph Neural Network

TTPXHunter: Actionable Threat Intelligence Extraction as TTPs

from Finished Cyber Threat
Reports

Revolutionizing Cyber Threat Detection With Large Language

Models: A Privacy-Preserving
BERT-Based Lightweight Model for IoT/IIoT Devices

A Situation Based Predictive Approach for Cybersecurity

Intrusion Detection and Prevention Using
Machine
Learning and Deep Learning Algorithms in Wireless Sensor
Networks of Industry 4.0
Deep Learning in the Fast Lane: A Survey on Advanced Intrusion
Detection Systems for
Intelligent Vehicle Networks

Semantic Deep Hiding for Robust Unlearnable Examples

Secure Distributed Control for Demand Response in Power

Systems Against
Deception Cyber-Attacks With Arbitrary Patterns

Modeling Load Redistribution Attacks in Integrated Electricity-

Gas Systems

The Role of Deep Learning in Advancing Proactive Cybersecurity

Measures for Smart Grid Networks

Quantized Distributed Economic Dispatch for

Microgrids: Paillier Encryption-Decryption Scheme

Automated Knowledge-Based Cybersecurity Risk

Assessment of Cyber-Physical Systems

Attribute-hiding fuzzy encryption for privacy-preserving data

evaluation

Privacy-Preserving Naïve Bayesian Classification for Health

Monitoring Systems
Dynamic User Clustering for Efficient and Privacy-Preserving
Federated Learning

The Role of Cyber-Physical-Social Systems in Smart Energy

Future

Systematically Assessing the Security Risks of AI/ML-enabled

Connected Healthcare Systems

Cyber-Physical Testbed Co-Simulation Real-Time:

Normal and Abnormal System Frequency Response

A Game-Theoretical Scheme in the Smart Grid With Demand-

Side Management:
Towards a Smart Cyber-Physical Power
Infrastructure

Secure Relay Selection With Outdated CSI in Cooperative

Wireless Vehicular Networks: A DQN Approach

Depriving the Survival Space of Adversaries Against Poisoned

Gradients in Federated Learning

Learning Near-Optimal Intrusion Responses Against Dynamic

Attackers

Trusted Operations of a Military Ground Robot in the Face of

Man-in-the-Middle Cyberattacks Using Deep
Learning Convolutional Neural Networks: Real-Time
Experimental Outcomes
Optimal Finite Horizon Scheduling of Wireless Networked
Control Systems

The Least Increasing Aversion (LIA) Protocol: Illustration on

Identifying Individual Susceptibility to
Cybersickness Triggers

Temporal Characterization and Prediction of VR Traffic: A

Network Slicing Use Case

Gotham Testbed: A Reproducible IoT Testbed for Security

Experiments and Dataset Generation

A Situation Based Predictive Approach for Cybersecurity

Intrusion Detection and Prevention Using Machine
Learning and Deep Learning Algorithms in Wireless Sensor
Networks of Industry 4.0

Deep Learning in the Fast Lane: A Survey on Advanced Intrusion

Detection Systems forIntelligent Vehicle Networks

Semantic Deep Hiding for Robust Unlearnable Examples

Secure Distributed Control for Demand Response in Power

Systems AgainstDeception Cyber-Attacks With Arbitrary
Patterns

Modeling Load Redistribution Attacks in Integrated Electricity-

Gas Systems

An Unsupervised Adversarial Autoencoder forCyber Attack

Detection in Power Distribution Grids

The Role of Deep Learning in Advancing Proactive Cybersecurity

Measures for Smart Grid Networks

Quantized Distributed Economic Dispatch for Microgrids: Paillier

Encryption-Decryption Scheme
Automated Knowledge-Based Cybersecurity Risk Assessment of
Cyber-Physical Systems

Attribute-hiding fuzzy encryption for privacy-preserving data

evaluation

Privacy-Preserving Naïve Bayesian Classification for Health

Monitoring Systems

Dynamic User Clustering for Efficient and Privacy-Preserving

Federated Learning

The Role of Cyber-Physical-Social Systems in Smart Energy

Future

Systematically Assessing the Security Risks of AI/ML-enabled

Connected Healthcare Systems

Cyber-Physical Testbed Co-Simulation Real-Time:Normal and

Abnormal System Frequency Response

A Game-Theoretical Scheme in the Smart Grid With Demand-

Side Management:Towards a Smart Cyber-Physical Power
Infrastructure

Secure Relay Selection With Outdated CSI in Cooperative

Wireless Vehicular Networks: A DQN Approach
Depriving the Survival Space of Adversaries Against Poisoned
Gradients in Federated Learning

Learning Near-Optimal Intrusion Responses Against Dynamic

Attackers

Trusted Operations of a Military Ground Robot in the Face of

Man-in-the-Middle Cyberattacks Using Deep
Learning Convolutional Neural Networks: Real-Time
Experimental Outcomes

Optimal Finite Horizon Scheduling of Wireless Networked

Control Systems

DARD: Deceptive Approaches for Robust Defense Against IP

Theft

The Least Increasing Aversion (LIA) Protocol: Illustration on

Identifying Individual Susceptibility to Cybersickness Triggers

Temporal Characterization and Prediction of VR Traffic: A

Network Slicing Use Case

Gotham Testbed: A Reproducible IoT Testbed for Security

Experiments and Dataset Generation

MEL: Efficient Multi-Task Evolutionary Learning for High-

Dimensional Feature Selection
A Hybrid Air Quality Prediction Model Based on Empirical
Mode Decomposition language

E-Commerce Fraud Detection Based on Machine Learning

Techniques: Systematic Literature Review

Gender-Based Analysis of User Reactions to Facebook Posts

Predicting_Energy_Consumption_Using_Stacked_LSTM_Snapsh
ot_Ensemble

A Cost-Sensitive Machine Learning Model With Multitask

Learning For Intrusion Detection In Iot

Pretrained_Quantum-
Inspired_Deep_Neural_Network_for_Natural_Language_Processi
ng

A Novel Recommendation Algorithm Integrates Resource

Allocation and Resource Transfer in Weighted Bipartite Network

Leveraging_Gametic_Heredity_in_Oversampling_Techniques_to
_Handle_Class_Imbalance_for_Efficient_Cyberthreat_Detection_
in_IIoT

Classification of Tolerances in Permanent Magnet Synchronous

Machines With Machine Learning
A Cost-Sensitive Machine Learning Model With Multitask
Learning for Intrusion Detection in IoT

An IoMT-Based Incremental Learning Framework With a Novel

Feature Selection Algorithm for Intelligent Diagnosis in Smart
Healthcare

Exploring Classification of Topological Priors With Machine

Learning for Feature Extraction

Multilayer Perceptron Neural Network Approach to Classifying

Learning Modalities Under the New Normal

A Novel Recommendation Algorithm Integrates Resource

Allocation and Resource Transfer in Weighted Bipartite Network

Vaccine Hesitancy Hotspots in Africa: An Insight From

Geotagged Twitter Posts

Forecasting Gender in Open Education Competencies: A Machine

Learning Approach

A Multi-perspective Fraud Detection Method for Multi-

Participant E-commerce Transactions
FRHIDS: Federated Learning Recommender Hybrid Intrusion
Detection System Model in Software-Defined Networking for
Consumer Devices

Attention-Based Hybrid Deep Learning Model for EEG Emotion

Recognition

SAFER-STUDENT for Safe Deep Semi-Supervised Learning

With Unseen-Class Unlabeled Data

Extensible Machine Learning for Encrypted Network Traffic

Application Labeling via Uncertainty Quantification

Hybrid Models for Knowledge Tracing: A Systematic Literature

Review

Multi-Branch Mutual-Distillation Transformer for EEG-Based

Seizure Subtype Classification

A Novel CNN-BiLSTM Ensemble Model With Attention

Mechanism for Sit-to-Stand Phase Identification Using Wearable
Inertial Sensors
An_Introduction_to_Adversarially_Robust_Deep_Learning

Deep_Learning_for_Electromyographic_Lower-
Limb_Motion_Signal_Classification_Using_Residual_Learning

DiffMDD_A_Diffusion-
Based_Deep_Learning_Framework_for_MDD_Diagnosis_Using
_EEG

From_Clustering_to_Cluster_Explanations_via_Neural_Networks

Learning_Random_Access_Schemes_for_Massive_Machine-
Type_Communication_With_MARL

Machine-to-Machine_Transfer_Function_in_Deep_Learning-
Based_Quantitative_Ultrasound
Otago_Exercises_Monitoring_for_Older_Adults_by_a_Single_I
MU_and_Hierarchical_Machine_Learning_Models

Physics-
Informed_Deep_Learning_for_Muscle_Force_Prediction_With_
Unlabeled_sEMG_Signals

Semi-Supervised_Learning_for_Multi-
Label_Cardiovascular_Diseases_Prediction_A_Multi-
Dataset_Study

Stealthy_Adversarial_Attacks_on_Machine_Learning-
Based_Classifiers_of_Wireless_Signals
Targeted-
BEHRT_Deep_Learning_for_Observational_Causal_Inference_o
n_Longitudinal_Electronic_Health_Records

Test_Input_Prioritization_for_Machine_Learning_Classifiers

Unleashing_the_Potential_of_Knowledge_Distillation_for_IoT_T
raffic_Classification

A Weighted Stacking Ensemble Model With Sampling for Fake

Reviews Detection

An Explainable and Resilient Intrusion Detection System for

Industry 5.0

Resource-Constraint Deep Forest based Intrusion Detection

Method in Internet of Things for Consumer Electronic

Micro-Expression Recognition Based on Nodal Efficiency in the

EEG Functional Networks
High Precision Traffic Flow Reconstruction via Hybrid Method

Time-series Failure Prediction on Small Datasets Using Machine

Learning

Application of Quantum Recurrent Neural Network in Low-

Resource Language Text Classification

Self-Supervised Learning-Based General Laboratory Progress

Pretrained Model for Cardiovascular Event Detection

Deep Ensemble Learning With Pruning for DDoS Attack

Detection in IoT Networks

Classifying Routine Clinical Electroencephalograms With

Multivariate Iterative Filtering and Convolutional Neural
Networks

Exploring COVID-19 Trends in Mexico During the Winter

Season with Explainable Artificial Intelligence (XAI)
Applying Competition-Based Learning to Stimulate Students’
Practical and Competitive AI Ability in a Machine Learning
Curriculum

Traffic Data-Empowered XGBoost-LSTM Framework for

Infectious Disease Prediction

A deep multimodal fusion and multitasking trajectory prediction

model for typhoon trajectory prediction to reduce flight
scheduling cancellation

Achieving Multi-Time-Step Segment Routing via Traffic

Prediction and Compressive Sensing Techniques

Long-Term Prediction of Sea Surface Temperature by Temporal

Embedding Transformer With Attention Distilling and Partial
Stacked Connection

EMG-based Multi-User Hand Gesture Classification via

Unsupervised Transfer Learning Using Unknown Calibration
Gestures

Indirect Estimation of Breathing Rate Using Wearable Devices

Advances and Challenges in Meta-Learning: A Technical Review

A Multi-Modal Classification Method for Early Diagnosis of

Mild Cognitive Impairment and Alzheimer’s Disease Using Three
Paradigms With Various Task Difficulties

Digital Twinning of Cardiac Electrophysiology Models From the

Surface ECG: A Geodesic Backpropagation Approach

Deep Learning for Radio Resource Allocation Under DoS Attack

Incremental Adversarial Learning for Polymorphic Attack

Detection
Towards Real-time Network Intrusion Detection with Image-
based Sequential Packets Representation

Otago Exercises Monitoring for Older Adults by a Single IMU

and Hierarchical Machine Learning Models

Efficient Frequent Chronicle Mining Algorithms: Application to

Sleep Disorder

Flood Inundation Extraction and its Impact on Ground

Subsidence Using Sentinel-1 Data: A Case Study of the “7.20”
Rainstorm Event in Henan Province, China

Sea Surface Signal Extraction for Photon-Counting LiDAR Data:

A General Method by Dual-Signal Unmixing Parameters

Enhancing Telemarketing Success Using Ensemble-Based Online

Machine Learning

MAST: An Earthquake-Triggered Landslides Extraction Method

Combining Morphological Analysis Edge Recognition With
Swin-Transformer Deep Learning Model

Deep Learning and Machine Learning Approaches for Brain

Hemorrhage Detection
An Efficient Method for Detecting Dense and Small Objects in
UAV Images

LS-YOLO: A Novel Model for Detecting Multiscale Landslides

With Remote Sensing Images

FsrGAN: A Satellite and Radar-Based Fusion Prediction Network

for Precipitation Nowcasting

Deep Learning-Based Assessment Model for Real-Time

Identification of Visual Learners Using Raw EEG

Eye-LRCN: A Long-Term Recurrent Convolutional Network for

Eye Blink Completeness Detection

Deep Ensemble Learning With Pruning for DDoS Attack

Detection in IoT Networks

Bad and Good Errors: Value-Weighted Skill Scores in Deep

Ensemble Learning

Improving Generalization of ML-Based IDS With Lifecycle-

Based Dataset, Auto-Learning Features, and Deep Learning
Streamlining ID card Generation and Management with Django

Bid Bazaar using Django

Hospital Management System using Django

Agri shop- Farmer online selling application

Streamlining ID card Generation and Management with Django

Therapist chatbot for Medical assistance A Django framework

Django-Parking Management System using yolo

Online complaints Portal using Django

Benefit Bot – Government Scheme Chatbot

Ride Rentals using Django

Meal Metric using Django

Block chain-Based Voting System

A build in quility report maintanace using block chain using Data

Science

Question Bank Recommendation and online Examination by Dual

mode operation system

A session of multi task manager for file converter

AI generated Color Formula in Paint Industry

Portfolio Website in Python using Django

Real Estate Listings Website

YouTube : Statistical Analysis Tool

DjangoMart: Online Marketplace

E-learning Platform

E-Commerce Website for Visually Impaired

Online Paying Guest Accommodation Project

Advanced Employee Management System Project

Industrial Visit Planning & Booking System

Software Recommendation by AI Machine Learning

Customer Relationship Management by Sentiment Analysis in AI

technology

A statistics and visualization of data analytics in social media

APP data

A taste of Tea - Customer Review and product recommendation

in Web APP
Task Scheduling and Productivity sheet security using block
chain technology

Step into Success - A Student performance analysis for future

scope

Beauty Sketchy – Sketch making Flask App

URL Shortener using Flask and Phising Attack Detection

Flipkart Reviews extraction and sentiment analysis with Flask

app

Medical Assist : Doctor-Patient Appointment System in Python

using Flask

IPL Score Prediction with Flask app

SBERT : Sentence-BERT for text summarization

Corruption : Complaint Assist System using flask

OSTR : Online Survey Tool and Review

Equip Yourself : Expense Tracker

FlaskHRM: Human Resource Management System

Event Planning and Management

Legal Document Automation Platform

Buy One Get One : BOGO - Offer tracking system

BoNuS: Boundary Mining for Nuclei Segmentation with Partial

Point Labels
Ultrasound Nodule Segmentation Using Asymmetric Learning
with Simple Clinical Annotation
Multiple Latent Space Mapping for Compressed Dark Image
Enhancement

Anomaly Detection for Medical Images Using Teacher–Student

Model With Skip Connections Mingxuan Liu and Multiscale
Anomaly Consistency

Learning Decentralized Traffic Signal Controllers with Multi-

Agent Graph Reinforcement Learning

Analysis of Brain Imaging Data for the Detection of Early Age

Autism Spectrum Disorder Using Transfer Learning Approaches
for Internet of Things

Development of Convolutional Neural Network to Segment

Ultrasound Images of Histotripsy Ablation
IACC: Cross-Illumination Awareness and Color Correction for
Underwater Images Under Mixed Natural and Artificial Lighting

Federated-Reinforcement Learning-Assisted IoT Consumers

System for Kidney Disease Images

A Deep Quantum Convolutional Neural Network Based Facial

Expression Recognition For Mental Health Analysis

Light-weight Retinal Layer Segmentation with

Deep Omni-supervised Learning for Rib Fracture Detection from

Chest Radiology Images

Multi-Task Learning for Fatigue Detection and Face Recognition

of Drivers via Tree-Style Space-Channel Attention Fusion
Network

Automatic Accident Detection, Segmentation and Duration

Prediction Using Machine

Enhanced Biometric Template Protection Schemes for Securing

Face Recognition in IoT Environment
DiffWater: Underwater Image Enhancement Based on
Conditional Denoising Diffusion Probabilistic Model

AIROGS: Artificial Intelligence for Robust Glaucoma Screening

Challenge

TRTAR: Transmissive RIS-assisted Through-the-wall Human

Activity Recognition

ChatCAD+: Towards a Universal and Reliable Interactive CAD

using LLMs

A Colorectal Coordinate-Driven Method for Colorectum and

Colorectal Cancer Segmentation in Conventional CT Scans

Recurrent Generic Contour-based Instance Segmentation with

Progressive Learning

Joint Learning of Blind Super-Resolution and Crack

Segmentation for Realistic Degraded Images

Light-weight Retinal Layer Segmentation with Global Reasoning

CM-MaskSD: Cross-Modality Masked\ Self-Distillation for
Referring Image Segmentation

From Canteen Food to Daily Meals: Generalizing Food

Recognition to More Practical Scenarios

Harvard Glaucoma Fairness: A Retinal Nerve Disease Dataset for

Fairness Learning and Fair Identity Normalization

A Review of Building Extraction From Remote Sensing Imagery:

Geometrical Structures and Semantic Attributes

Enhancing Contrastive Learning With Positive Pair Mining for

Few-Shot Hyperspectral Image Classification

Mean-Weighted Collaborative Representation-Based Spatial-

Spectral Joint Classification for Hyperspectral Images

Lossless Data Hiding in NTRU Cryptosystem by Polynomial

Encoding and Modulation

An Interpretable and Accurate Deep-Learning Diagnosis

Framework Modeled With Fully and Semi-Supervised Reciprocal
Learning

High-Frequency Space Diffusion Model for Accelerated MRI

A Test Statistic Estimation-Based Approach for Establishing Self-
Interpretable CNN-Based Binary Classifiers

Multi-view learning for automatic classification of multi-

wavelength auroral images

Time Efficient Ultrasound Localization Microscopy Based on A

Novel Radial Basis Function 2D Interpolation

Guided Filter of Random Patches Network and Relaxed-

Collaborative-Representation-Based Hyperspectral Image
Classification

Active Learning-Based Spectral–Spatial Classification for

Discriminating Tree Species in Hyperspectral Images

Protocol-Based Distributed Security Fusion Estimation for Time-

Varying Uncertain Systems Over Sensor Networks: Tackling DoS
Attacks

Toward Robust and Unconstrained Full Range of Rotation Head

Pose Estimation

Field-to-Field Coordinate-Based Segmentation Algorithm on

Agricultural Harvest Implements

Ensemble Image Explainable AI (XAI) Algorithm for Severe

Community-Acquired Pneumonia and COVID-19 Respiratory
Infections
Edge-Computing-Enabled Deep Learning Approach for Low-
Light Satellite Image Enhancement

An Efficient Method for Detecting Dense and Small Objects in

UAV Image

Conventional to Deep Ensemble Methods for Hyperspectral

Image Classification: A Comprehensive Survey

Deep Evidential Remote Sensing Landslide Image Classification

With a New Divergence, Multiscale Saliency and an Improved
Three-Branched Fusion

FsrGAN: A Satellite and Radar-Based Fusion Prediction Network

for Precipitation Nowcasting

Unsupervised Human Activity Recognition Learning for

Disassembly Tasks

Exploring Deep Learning and Machine Learning Approaches for

Brain Hemorrhage Detection

A Novel Grading Biomarker for the Prediction of Conversion

from Mild Cognitive Impairment to Alzheimer’s Disease
Machine_Learning_Analysis_of_Human_Skin_by_Optoacoustic_
Mesoscopy_for_Automated_Extraction_of_Psoriasis_and_Aging
_Biomarkers

Data-Driven Low-Complexity Detection in Grant-Free NOMA

for IoT

A Cold Start Recommendation System based on Item Correlation

and User Similarity

A Collaborative Defence Framework Against DDoS Attacks

detection system Using Network Function Virtualization

An Auction-Based Mechanism for Efficient Resource

Procurement in Cloud Computing

A Communication-Based Scheduling Scheme for Energy

Management system in Consumer-Premise Systems

An Image Filtering and Re-Ranking Approach in the Compressed

Domain for Multi-Agent image Retrieval Systems

Dynamic User Authorization for A Computational Trust Model

A Context-Aware Word Indexing Model generation for

Document Summarization
A Coordinator for data Scaling Elastic Applications Across
Multiple Cloud Environments
A Decentralized Cloud Firewall Framework with Cost
Optimization for Resource Provisioning in cloud computing
A massive Cloud Environments for A Dynamic and Load-
Balanced Flow Scheduling Approach for Big Data Centres

CSPPartial-YOLO: A Lightweight YOLO-Based Method for

Typical Objects Detection in Remote Sensing Images
Detection of SAR images multiscale ship targets in complex
inshore scenes based on improved yolo v5IEEE

An Improved Extreme Learning Machine (ELM) Algorithm for

Intent Recognition of Transfemoral Amputees With Powered
Knee Prosthesis

Analysis of Cancer-associated Mutations of POLB using Machine

Learning and Bioinformatics

BIOWISH: Biometric Recognition Using Wearable Inertial

Sensors Detecting Heart Activity

The Extent of AI Applications in EFL Learning and Teaching

Applying Competition-Based Learning to Stimulate Students’
Practical and Competitive AI Ability in a Machine Learning
Curriculum

Artificial Intelligence and Machine Learning for Improving

Glycemic Control in Diabetes: Best Practices, Pitfalls, and
Opportunities

Hybrid Optimization Algorithm for Detection of Security Attacks

in IoT-Enabled Cyber-Physical Systems

Enhancing SSVEP-BCI Performance Under Fatigue State Using

Dynamic Stopping Strategy

Epileptic Seizure Detection Based on Path Signature and Bi-

LSTM Network With Attention Mechanism

Characterizing Disease Progression in Parkinson’s Disease from

Videos of the Finger Tapping Test

A Self-Labeling Method for Adaptive Machine Learning by

Interactive Causality
Machine Learning Analysis of Human Skin by Optoacoustic
Mesoscopy for Automated Extraction of Psoriasis and Aging
Biomarkers

Machine Learning on Multiplexed Optical Metrology Pattern

Shift Response Targets to Predict Electrical Properties

Multi-Task Heterogeneous Ensemble Learning-Based Cross-

Subject EEG Classification Under Stroke Patients

Real-Time Precise Targeting of the Subthalamic Nucleus via

Transfer Learning in a Rat Model of Parkinson’s Disease Based
on Microelectrode Arrays
Performance Assessment of an ITU-T Compliant Machine
Learning Enhancements for 5G RAN Network Slicing

Multitask and Transfer Learning Approach for Joint

Classification and Severity Estimation of Dysphonia

A Hybrid Air Quality Prediction Model Based on Empirical

Mode Decomposition

Knee-Point-Conscious Battery Aging Trajectory Prediction Based

on Physics-Guided Machine Learning

Privacy-Preserving Federated Class-Incremental Learning

Analysis of Brain Imaging Data for the Detection of Early Age

Autism Spectrum Disorder Using Transfer Learning Approaches
for Internet of Things

Deep Learning for Electromyographic Lower-Limb Motion

Signal Classification Using Residual Learning

Navigation Learning Assessment Using EEG-Based Multi-Time

Scale Spatiotemporal Compound Model
KFDAE: CircRNA-Disease Associations Prediction Based on
Kernel Fusion and Deep Auto-Encoder

Graph Neural Network-Based EEG

Classification: A Survey

B2-ViT Net: Broad Vision Transformer Network With

Broad Attention for Seizure Prediction

Multi-Task Collaborative Network: Bridge the Supervised and

Self-Supervised Learning for EEG Classification in RSVP Tasks

Physiologic Network-Based Brain-Heart Interaction

Quantification During Visual Emotional Elicitation

An Overview of the ADReSS-M Signal Processing Grand

Challenge on Multilingual Alzheimer's Dementia Recognition
Through Spontaneous Speech

Heart Failure Prediction System

Deep Learning-based Design of Uplink Integrated Sensing and

Communication

SDOA-Net: An Efficient Deep Learning-Based DOA Estimation

Network for Imperfect Array
Unleashing Dynamic Pipeline Reconfiguration of P4 Switches for
Efficient Network Monitoring

Capacitated Shortest Path Tour-Based Service Chaining Adaptive

to Changes of Service Demand and Network Topology

Cricket Club Management

Asymmetric SVPWM and Error Suppression Method for Current

Reconstruction of T-type Three-Level Inverter

An Energy Based Model of Four Switch BuckBoost Converter

A Review of Broadband Frequency Techniques for Insulation

Monitoring and Diagnosis in Rotating Electrical Machines

Optimized 9-Level Switched-Capacitor Inverter for Grid-

Connected Photovoltaic System

Virtual Synchronous Machine Control for Asynchronous Grid

Connections

Reconfiguration of Bipolar HVDC System for Continuous

Transmission Under DC Line Fault

30 kW Bidirectional Inductive Power Transfer Charger With

Intermediate Coil for EV Applications
Novel Hermite Interpolation-Based MPPT Technique for
Photovoltaic Systems Under Partial Shading Conditions

Over 98% Efficiency SiC-MOSFET based Four-Phase

Interleaved Bidirectional DC-DC Converter Featuring Wide-
Range Voltage Ratio

High-efficiency Modulation Scheme for Three-Level Buck Four-

Leg Current-Source Inverter

General and Unifed Model of the Power Flow Problem in

Multiterminal AC/DC Networks

A Wireless Self-Powered I-V Curve Tracer for On-Line

Characterization of Individual PV Panels

Advancing Electric Vehicle Charging Ecosystems with Intelligent

Control of DC Microgrid Stability

A Soft-switched Multi-port Converter for PV/Supercapacitors

Hybrid Systems enabling
Frequency Response Services

Impact of DC-Link Voltage Control on Torsional Vibrations in

Grid-Forming PMSG Wind Turbines

Multi-scale Fusion Model Based on Gated Recurrent Unit for

Enhancing Prediction Accuracy of State-of-charge in Battery
Energy Storage Systems

An_Energy-Based_Model_of_Four-
Switch_BuckBoost_Converter
Centralised Multimode Power Oscillation Damping Controller for
Photovoltaic Plants With Communication Delay Compensation

Decentralized_Dynamic_Power_Sharing_Control_for_Frequency
_Regulation_Using_Hybrid_Hydrogen_Electrolyzer_Systems

Gain and Phase: Decentralized Stability Conditions for Power

Electronics-Dominated Power Systems

Fast and Accurate Non-linear Model for Synchronous Machines

Including Core Losses

Predicting DC-Link Capacitor Current Ripple in AC-DC Rectifier

Circuits Using Fine-Tuned Large
Language Models

Capacitor Voltage Balancing Method for the Hybrid Multilevel

Converter Considering Grid Voltage Sags

Progress in artificial intelligence applicationsbasedon the

combination of self-driven sensorsanddeeplearning

Effective Application of IoT Power Electronics Technology and

Power System Optimization Control

Efficient and Fast Wind Turbine MPPT Algorithm Using TS

Fuzzy Logic and Optimal Relation
Methods
Genetic Algorithm-Based Optimal Sizing of Hybrid
Battery/Ultracapacitor Energy Storage
System for Wave Energy Harvesting Applications

PowerFlowMultiNet: Multigraph Neural Networks for

Unbalanced Three-Phase Distribution Systems

Reclosers Modeling for Temporal Simulation of Distribution

Networks in Simulink/Matlab

Multi-Micro Grid System Reinforcement Across Deregulated

Markets, Energy Resources
Scheduling and Demand Side Management Using a MultiAgent-
Based Optimization
in Smart Grid Paradigm

Passivity and Decentralized Stability Conditions for Grid-

Forming Converters

Quantitative Stability Conditions for Grid-Forming Converters

With Complex Droop Control

Distributed Control of Islanded DC Microgrids: A Passivity-

Based Game Theoretical Approach
A Coordinated Multitimescale Model Predictive Control for
Output Power Smoothing in Hybrid
Microgrid Incorporating Hydrogen Energy Storage

PowerFlowMultiNet: Multigraph Neural Networks for

Unbalanced Three-Phase Distribution Systems

FaultSSL: Seismic Fault Detection via Semi-supervised learning

Convex Optimal Power Flow Based on Power Injection-based

Equations and Its Application in
Bipolar DC Distribution Network

PowerFlowMultiNet: Multigraph Neural Networks for

Unbalanced Three-Phase Distribution Systems

Attention-Based CNN Fusion Model for Emotion Recognition

During Walking Using Discrete Wavelet Transform on EEG and
Inertial Signals

Multi-Scale Masked Autoencoders for Cross-Session Emotion

Recognition

Multi-Modal Sleep Stage Classification With Two-Stream

Encoder-Decoder
Attention Mechanism
Role of AI in regulating the time table scheduling

Mood Swing Analysis using Artificial Analysis

End to End Encryption in financial documents using voice

command

Online Paid Advertising Web Application

On Road Vehicle Breakdown Assistance Finder

Artificial Intelligence assisted Stock Management System

Price Negotiator Ecommerce ChatBot System

Low Complexity VLSI Architecture for OTFS Transceiver under
Multipath Fading Channel

High-Throughput Bilinear Pairing Processor forServer-Side

FPGA Applications

Low Complexity VLSI Architecture for OTFS Transceiver under

Multipath Fading Channel

Stream Processing Architectures for Continuous ECG Monitoring

Using SubsamplingBased Classifiers
FELIX: FPGA-Based Scalable and Lightweight Accelerator for
Large Integer Extended GCD

Enabling HW-Based Task Scheduling in Large Multicore

Architectures

Noise Analysis and Design Methodology of Chopper Amplifiers

With Analog
DC-Servo Loop for Biopotential Acquisition Applications
An Open-Source Tool to Model and Explore Complex Routing
Architecture for FPGA

MaliGNNoma: GNN-Based Malicious Circuit Classifier for

Secure Cloud FPGAs

HUB Meets Posit: Arithmetic Units Implementation

Energy-Efficient Exposed Datapath Architecture With a RISC-V

Instruction Set Mode

STAR-RIS Aided Secure MIMO Communication Systems

Towards Real-time Network Intrusion Detection with Image-

based Sequential Packets Representation

Interleaved Training for Massive MIMO Downlink via Exploring

Spatial Correlation

Energy-Efficient Distributed Spiking Neural Network for

Wireless Edge Intelligence
FDA-MIMO Transmitter and Receiver Optimization

OFDM-Based Active STAR-RIS-Aided Integrated Sensing and

Communication System

Enhancing Resource Utilization of Non-terrestrial Networks

Using Temporal Graph-based
Deterministic Routing

Robust Resource Allocation for STAR-RIS Assisted SWIPT

Systems

Deep Reinforcement Learning for Multi-User RF Charging with

Non-linear Energy Harvesters

Analysis of IRS-Assisted Downlink Wireless Networks over

Generalized Fading

Enabling Deep Learning-based Physical-layer Secret Key

Generation for FDD-OFDM Systems in
Multi-Environments

RL-based Relay Selection for Cooperative WSNs in the Presence

of Bursty Impulsive Noise

Control-Oriented Deep Space Communications For Unmanned

Space Exploration
Super-Resolution Estimation of UWB Channels including the
Dense Component — An SBL-Inspired Approach

Frequency-Switchable Routing Protocol for Dynamic Magnetic

Induction-Based Wireless
Underground Sensor Networks

A Safe Deep Reinforcement Learning Approach for Energy

Efficient Federated Learning
in Wireless Communication Networks

Semantic Utility Loss of Information for Energy Efficient

Semantic Status Update Communications

Hybrid Active-Passive RIS Transmitter Enabled Energy-Efficient

Multi-User Communications
Privacy and Security in Ubiquitous Integrated Sensing and
Communication: Threats, Challenges
and Future Directions

Decentralized Federated Learning: A Survey on Security and

Privacy

Benefits of V2V communication in connected and autonomous

vehicles in the presence of delays in
communicated signals

DeepSense-V2V: A Vehicle-to-Vehicle Multi-Modal Sensing,

Localization, and Communications Dataset

A Dynamic and Efficient Self-Certified Authenticated Group Key

Agreement Protocol for
VANET

Dynamic Cooperative MAC Optimization in RSU-Enhanced

VANETs: A Distributed Approach

Intelligent Reflecting Surfaces Assisted Cellular V2X based Open

RAN Communications

Performance Characterization of Joint Communication and

Sensing with Beyond 5G NR-V2X Sidelink

End-to-End Autonomous Driving through V2X Cooperation

Unified End-to-End V2X Cooperative Autonomous Driving

Virtual Sensor for Real-Time Bearing Load Prediction Using

Heterogeneous Temporal Graph Neural Networks

FDA-MIMO Transmitter and Receiver Optimization

Integrated Sensing and Communication with Massive MIMO: A

Unified Tensor Approach for
Channel and Target Parameter Estimation

Exploiting Active RIS in NOMA Networks with Hardware

Impairments

Covert Communication of STAR-RIS Aided NOMA Networks

Finite SNR Diversity-Multiplexing Trade-off in Hybrid

ABCom/RCom-Assisted NOMA Systems

Achievable Rate Analysis of Intelligent Omni-Surface Assisted

NOMA Holographic
MIMO Systems
Power-Level-Design-aware Scalable Framework for Throughput
Analysis of GF-NOMA in mMTC
Abstract

In today’s fast-paced world, the complexity of human emotions often leaves individuals feeling like a ship navigating turbu

Imagine a digital companion equipped with algorithms and deep learning techniques that continuously learns from daily int
whether it be social media interactions, sleep patterns, or seasonal changes.

The power of Natural Language Processing (NLP) propels AI systems to analyze the sentiments of your spoken or written w
portfolio, illuminating with alarming clarity when those evocative swings arise.

Combine this with data from wearables, and you have a revolution in mood analysis. Heart rate variability, sleep quality, an
physiological changes with emotional states.

In today's fast-paced financial markets, the integration of Artificial Intelligence (AI) into stock price management systems h
machine learning algorithms and predictive analytics to forecast market trends, optimize trading strategies, and enhance dec
actionable insights that help investors and traders navigate market volatility with greater precision and confidence. Its abilit
traditional methods. The system employs sophisticated techniques such as natural language processing, neural networks, an
geopolitical events. As a result, users benefit from a more holistic view of market dynamics, allowing for more informed in
complex and competitive environment.

Real-Time Span Data Recognizer System utilizing AI technology is an advanced application designed to process and analy
dynamic data streams, extracting valuable insights from temporal data inputs. The AI-driven backend continuously monitor
reports, and providing actionable insights. Its applications range from monitoring financial markets and managing operation
rapidly changing environments, ensuring timely and informed responses based on up-to-date information.

A Semantic Assist: Guidance Chatbot System using AI is an advanced web application designed to provide users with intel
to understand and respond to user queries with high accuracy. The system is capable of interpreting the intent behind user q
models and deep learning techniques, the chatbot continually improves its understanding of user inputs and refines its respo
deliver nuanced responses ensures that users receive precise guidance, making it an invaluable tool for enhancing user expe

An Efficient Recommendation of User Wishlist Using AI with Python is a cutting-edge system designed to enhance user ex
to generate accurate and relevant suggestions for products or services. Python's powerful libraries, such as TensorFlow and
time, offering dynamic and adaptive recommendations that improve over time as more data is collected. Users benefit from
engagement and increases conversion rates by presenting users with products they are more likely to find appealing and rel

Smart Finder: A Spam Detection Method in Messages Using AI with Python is an innovative application designed to identi
characteristics typical of spam. Utilizing Python’s powerful libraries, such as TensorFlow and scikit-learn, the application i
classification models to flag or filter out spam content while allowing legitimate messages to pass through. This ensures use
adapting from new data, Smart Finder enhances its detection capabilities, providing a reliable and efficient solution for man

Elegant Twin Face Analyzer using AI with Python is a sophisticated application designed to analyze and compare facial fea
leveraging Python’s powerful libraries such as OpenCV and TensorFlow. The application employs deep learning models to
and similarity scoring, providing a seamless and intuitive interface for users to upload and analyze images. By automating t
accurately identify twin faces makes it an invaluable tool for researchers, professionals, and enthusiasts interested in advanc

Control Me: Voice Assistance for System Controls using Python is an advanced application designed to enable hands-free m
control various aspects of their computer or application environment using natural language. The application processes spo
Me offers an intuitive and accessible way to interact with systems, making it especially beneficial for users with physical di
design and reliable performance, Control Me transforms voice interactions into effective system management tools, enhanc

This project focuses on developing a digit recognition system using artificial intelligence (AI) to accurately identify and cla
such as the MNIST dataset. The AI model learns to extract features and patterns from the images, enabling it to distinguish
project aims to enhance data entry efficiency, reduce manual errors, and facilitate the development of smart applications tha
crucial. Additionally, the project explores optimization techniques to improve the model’s performance and generalization
technologies to create more comprehensive automated systems.
A Prior Forecasting of Stock Market Range Using AI Methods in Recent Trends with Python is an advanced application de
potential range of stock prices based on historical data and current market trends. Employing Python's powerful libraries, su
predictions. By analyzing patterns, market indicators, and historical performance, the AI-driven backend provides insights i
empowers investors and analysts with valuable information to make informed decisions, manage risk, and optimize trading

Place of Customer: AI-Based Customer Satisfaction Monitoring System using Python is an advanced application designed
insights into customer satisfaction levels. Utilizing Python’s robust libraries, such as Natural Language Processing (NLP) w
reviews, and social media comments. The AI algorithms detect sentiment, identify key issues, and categorize feedback into
concerns effectively. By integrating these AI-driven capabilities, the system enables proactive measures to improve custom

AI-Based Prediction of Harsh Conversations Between People using Python is an innovative application designed to identify
as chat logs or transcripts, to detect patterns indicative of aggressive or negative exchanges. Utilizing Python’s powerful lib
analysis, emotion recognition, and context understanding to predict instances of harsh language. The AI algorithms are train
time or through batch processing, providing alerts and detailed reports on potential issues. By integrating these predictive c

A Collaborative AI and ML Technique to Predict Good Quality Products and Recommend to Users using Python is an adva
insights to predict and suggest high-quality products tailored to individual user preferences.

AI-Powered Diagnostics and Personalized Medicine using a Python web app built with Streamlit is a cutting-edge solution
patient data, such as medical history, symptoms, and diagnostic results, to provide accurate and actionable insights. The int
sophisticated models trained on extensive medical datasets, the system can identify patterns and correlations that aid in earl
its user-friendly design and powerful AI capabilities, the platform enhances the precision of diagnostics, improves the perso

AI-Based Speech Practice System using Python is an innovative application designed to help users improve their pronuncia
generate accurate and natural-sounding speech. Python’s powerful libraries, such as Text-to-Speech (TTS) engines like gTT
feedback on pronunciation, offering users the opportunity to practice and refine their speaking abilities. By comparing user
the AI-Based Speech Practice System offers a practical tool for language learners, professionals, and anyone looking to imp

Engages with Real-World E-Learning to Enhance Learning Outcomes using Python is a dynamic application designed to br
and interactive learning modules to enrich the educational experience. Features include simulation-based learning, real-time

Advanced AI-Based Robot Navigation in Maze Detection using Python focuses on developing a sophisticated system for au
leverages advanced AI algorithms like reinforcement learning and pathfinding techniques to enable the robot to detect and t
its navigation strategy based on feedback and environmental changes, ensuring accurate and obstacle-free pathfinding. This

By forecasting future sales patterns and offering in-depth industry insights, this project uses artificial intelligence to transfo
integration of machine learning models with data visualization tools. The efficacy of the approach in detecting critical elem
capabilities, the system helps businesses drive growth and optimize strategy by providing comprehensive market data, grea
analytics and integrating external data sources. Furthermore, the system's user-friendly interface makes it easy for departme

AI Face Enhancer using Python is a sophisticated application designed to improve and enhance facial images through advan
features, adjust lighting, remove imperfections, and apply aesthetic modifications. The AI models are trained on extensive d
controls for users to adjust enhancement levels, apply filters, and achieve professional-grade results. By leveraging AI’s cap
quality visual outcomes.
AI-Driven Battery Management and Optimization Technique using Python leverages advanced artificial intelligence to enh
libraries, such as TensorFlow and Scikit-learn, this system employs AI algorithms to monitor and optimize battery health an
Spam Email Detector Using Artificial Intelligence with Python is an advanced system designed to efficiently identify and f
language processing techniques to analyze and classify email content. By training on extensive datasets of labeled emails, t
its models with new data to enhance detection accuracy and adapt to evolving spam tactics. Featuring real-time email scann
email management.
Real-Time Translation Tool using Python is an advanced application designed to instantly translate text into multiple langu
translation models, the tool delivers seamless real-time translations. By integrating state-of-the-art machine learning and na
supports smooth and effective multilingual interactions, making it an invaluable resource for travelers, international busines
facilitating effortless communication across different languages.

Sentiment Analysis of Social Media Using Artificial Intelligence with Python is a powerful application designed to analyze
language processing techniques to assess the sentiment behind user-generated content across platforms like Twitter, Facebo
of social media data, the system identifies trends and patterns in public opinion, enabling businesses and organizations to ga
expressions of sentiment. With features for real-time analysis and visualizations, the Sentiment Analysis tool provides actio
sentiment analysis, the tool offers a comprehensive solution for understanding and leveraging social media dynamics.

Application of Translation Technology Based on AI in Translation Teaching offers a transformative approach to language e
on their native language or preferred learning language, tailoring the educational content to individual needs. The system ut
new languages through familiar linguistic structures. By integrating features such as real-time translation, interactive exerci
in their native language, receive instant feedback, and progressively build their language skills with materials that are conte
deeper understanding and practical application of new languages.

Artificial Intelligence-Based Language Translation Platform using Python is a cutting-edge application designed to facilitat
intelligence and deep learning techniques to provide high-quality translations in real-time. The system utilizes sophisticated
translations in their desired language, supported by features such as context-aware translation, language detection, and adap
translations. By combining Python's powerful data processing capabilities with AI-driven translation technology, this platfo

Artificial Intelligence-Based Customer Churn Prediction Model for Business Market using Python is an advanced analytica
Pandas, this model employs sophisticated algorithms to analyze customer behavior and predict the likelihood of churn.

Use of Explainable AI to Interpret the Results of NLP Models for Sentiment Analysis Using Python involves leveraging ad
(SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations), with Python’s NLP librarie
breakdown of the model’s decision-making process by highlighting the contributions of individual words or phrases to the o
reliability of sentiment analysis in various applications, from customer feedback analysis to market research. By applying th
predictions.

An online auction system developed using Django framework facilitates a dynamic marketplace where administrators, vend
list products/services for auction, setting starting bids and auction durations. Bidders engage in competitive bidding, placing
vibrant and transparent online auction environment. Furthermore, the system incorporates features such as real-time notific
reporting tools to monitor platform performance, track key metrics, and identify trends, enabling informed decision-making
promoting fair competition, transparency, and efficiency, the Django-based online auction system establishes itself as a reli

The Advanced Commercial Entities Business Registry System, developed using Node.js, is a high-performance, scalable pl
transactions with minimal latency, ensuring swift and reliable processing. This implementation includes RESTful APIs for
framework that supports dynamic updates and scalable growth, making it ideal for managing complex business registries w

Fine-tuning financial processes to enhance workflow efficiency using Node.js involves developing a robust, scalable platfo
minimizing delays and improving overall responsiveness. Its event-driven architecture facilitates seamless integration with
infrastructure, allowing for the easy implementation of advanced features such as predictive analytics and dynamic dashboa

Developing the Odyssey Planner website for swiftly booking travel and events using Node.js involves creating a high-perfo
requests, real-time updates, and seamless integration with external APIs for availability and pricing information. The use of
approach not only enhances the user experience with fast, reliable performance but also allows for flexible, real-time adjust
A real-time application for Developer Symphony Blogs, built using Node.js, provides a dynamic platform for seamless con
and comment on blog entries in real-time. The application leverages WebSocket technology to ensure that all changes and n
and user activities. Node.js's scalability and modular architecture support the application’s growth and adaptability, making

Elevating store operations and management to the cosmos using Node.js and MySQL involves creating a cutting-edge, scal
efficient handling of inventory updates, sales transactions, and customer interactions. Coupled with MySQL, which provide
technologies enables seamless synchronization across multiple store locations, advanced analytics, and scalable growth, ult
Enhancing the e-commerce experience on online shopping platforms using Node.js and MySQL involves developing a resp
browsing, adding items to carts, and completing transactions, ensuring a smooth and responsive user experience. MySQL c
Together, these technologies support a seamless integration of dynamic content updates, personalized recommendations, an

Med Optima for a Futuristic Pharmacy Operational Suite, built with Node.js, represents an advanced solution for modernizi
inventory management, prescription tracking, and patient interactions, ensuring real-time updates and efficiency. This platf
Med Optima delivers a responsive and intuitive user experience, enhances operational accuracy, and supports future growth

The Next-Gen Automotive Sales Platform, featuring an interactive UI developed with React, offers a cutting-edge, user-cen
customize features, and interact with real-time inventory updates. By leveraging React’s efficient rendering and state mana
an intuitive and visually appealing interface, streamlining the sales process, and adapting seamlessly to evolving market tre
The AI-based Sentient Forge, incorporating Emotional Intelligence Solutions for decision-makers, represents a transformat
from various data sources, including communication patterns and behavioral metrics, to provide nuanced, context-aware rec
empathy and precision. By combining sophisticated AI with emotional analytics, Sentient Forge empowers leaders to make
A real-time chat application using Node.js leverages the platform's non-blocking, event-driven architecture to provide insta
real-time without delays or interruptions. This setup ensures smooth, responsive interactions and supports features like live
users simultaneously, delivering a reliable and engaging chat experience across various devices and platforms.
A Calendar-Schedule Management System developed with Node.js offers a robust, real-time solution for organizing and m
that users can access and modify their calendars without delays. The platform integrates seamlessly with external calendars
managing complex scheduling needs and large user bases, delivering an intuitive and reliable calendar management experie
A Weather Dashboard built with Node.js offers a sophisticated platform for managing and displaying meteorological data i
conditions are readily available. Users can interact with an intuitive interface to view current weather, forecasts, and histori
detailed weather insights tailored to individual needs.
A Job Portal developed using Node.js and Express provides a high-performance, scalable platform for job seekers and emp
RESTful APIs and handling routing efficiently. The system supports real-time features such as job application updates and
of managing high traffic and complex data interactions, ultimately enhancing the efficiency and effectiveness of the job sea
An Inventory Management System built with Node.js provides a robust, scalable solution for efficiently tracking and mana
processing, and data synchronization across multiple locations. It supports features such as real-time inventory tracking, au
accurate inventory control and operational efficiency in a dynamic and high-performance environment.
An Expense Tracker developed with Node.js and integrated with chart visualization tools offers a comprehensive solution f
seamless updates and performance. Chart visualization components present expense data through intuitive, interactive grap
decisions and managing their budget with enhanced clarity and ease.
A Node.js-based Employee Management System delivers a scalable and efficient solution for overseeing and streamlining w
with real-time updates and high responsiveness. It integrates features such as automated scheduling, payroll management, a
adapt to growing organizational needs and providing a comprehensive, efficient tool for managing all aspects of employee
A Real-time Polling Application built with Node.js leverages its asynchronous, event-driven architecture to facilitate instan
Node.js efficiently manages multiple concurrent connections and handles dynamic data updates, ensuring a smooth and resp
experience for users.
A Node.js-based Restaurant Ordering System provides an efficient, real-time platform for managing and processing custom
responsive experience for both customers and restaurant staff. The platform supports features such as real-time menu updat
order accuracy, making it an ideal solution for modernizing restaurant operations and enhancing customer service.
An Online Quiz Application developed with Node.js offers a dynamic, real-time platform for creating, managing, and parti
real-time feedback. The system supports features like instant question updates, interactive scoring, and leaderboards, all wh
providing instant, accurate results to users.
A Node.js-based Personal Journaling App offers a secure and responsive platform for users to document and manage their p
seamless writing experience. Key features include real-time syncing of entries across devices, customizable privacy setting
and well-organized digital journal with minimal latency and maximum security.
A Node.js-based Employee Feedback System provides a robust and scalable platform for collecting, managing, and analyzi
reporting. The platform supports features such as anonymous feedback, performance reviews, and real-time analytics, facili
the overall effectiveness of employee engagement and organizational improvement initiatives.
A Node.js-based Content Management System (CMS) offers a fast, scalable solution for managing and publishing digital c
features an intuitive user interface, flexible content management, and easy integration with other tools, making it ideal for u
An Online Learning Platform built with Node.js provides a dynamic, scalable solution for delivering educational content an
delivery, interactive quizzes, and live discussions. The system supports real-time updates and notifications, handles multipl
students to interact, access resources, and track progress with minimal latency and high reliability.
An ERP model for a cooked supply chain provides a comprehensive, integrated solution for managing and optimizing the e
and coordination across the supply chain. By centralizing data and automating workflows, the ERP system enhances operat
chain that adapts to market demands and regulatory requirements, ultimately driving better performance and customer satis
A Car Accessories Marketplace developed using Node.js offers a high-performance platform for buying and selling automo
management, and transaction processing efficiently. The platform supports features such as dynamic product listings, advan
and integrate with external systems, making it an ideal solution for connecting buyers and sellers in the automotive accesso
An e-commerce platform using Node.js and MongoDB delivers a high-performance, scalable solution for online shopping,
products, while MongoDB’s NoSQL database efficiently handles diverse product data and user profiles with dynamic, scala
The system’s ability to manage high traffic and large volumes of data enhances performance and scalability, making it idea
An e-commerce platform using Node.js and MongoDB delivers a high-performance, scalable solution for online shopping,
products, while MongoDB’s NoSQL database efficiently handles diverse product data and user profiles with dynamic, scala
The system’s ability to manage high traffic and large volumes of data enhances performance and scalability, making it idea
A News Web Application built with Node.js provides a dynamic and scalable platform for delivering up-to-date news conte
feeds efficiently. The system supports features such as real-time article publishing, user comments, and personalized news
informed with timely and relevant information.
A Bookstore Library Management System provides a comprehensive solution for efficiently handling book inventory, custo
customer activity. It supports features such as advanced search and filtering, automated notifications for due dates, and seam
optimizing resource use and improving service delivery.
A Media Streaming Application delivers a robust platform for streaming audio and video content seamlessly to users. Desig
large volumes of concurrent streams with minimal latency, leveraging advanced technologies for efficient data processing a
and network conditions.
A Company Visitor Management System streamlines the process of tracking and managing guest visits within a corporate e
user-friendly interface for scheduling appointments, verifying guest identities, and managing visitor access permissions. W
and improving overall visitor management.
A Company Visitor Management System streamlines the process of tracking and managing guest visits within a corporate e
user-friendly interface for scheduling appointments, verifying guest identities, and managing visitor access permissions. W
and improving overall visitor management.

A Notes Management System provides a streamlined, digital solution for organizing and managing personal and profession
cloud storage and synchronization across devices, users can access their notes anytime and from anywhere. The system sup

An Online FIR Management System provides a digital platform for efficiently filing, tracking, and managing First Informa
receiving updates on case progress. It features real-time status tracking, automated notifications, and integration with police
for both law enforcement personnel and the public.
A Faculty Profile Management System offers a comprehensive platform for organizing and maintaining detailed records of
teaching schedules. With an intuitive interface and secure data handling, the system facilitates easy access to faculty inform
time updates, ensuring efficient profile management and improved organizational transparency.
A Social Media Web Application offers a dynamic platform for users to connect, share, and interact within a virtual commu
supports multimedia content, customizable profiles, and activity feeds, while ensuring robust data security and privacy cont
platforms.
A Cinema Reservation System provides a streamlined, user-friendly platform for booking movie tickets and managing thea
secure payment processing, and automated booking confirmations and reminders. By integrating with theater management
both customers and cinema operators.
A Matrimonial System developed with Node.js provides a scalable and responsive platform for individuals seeking matrim
Features include advanced search filters, profile management, and secure communication channels. The platform handles h
connect with potential partners.
An E-Pass Management System offers a digital solution for issuing, managing, and verifying electronic passes for various p
automated approvals, and instant notifications. It integrates with databases for verification and validation, ensuring the accu
and improves overall user convenience.
A Stack Overflow clone built with MUI (Material-UI) and React delivers a modern, responsive platform for community-dri
with features such as question posting, voting, commenting, and user profiles. Real-time updates and efficient state manage
users to seek and share knowledge effectively in a scalable, visually appealing environment.

A Grocery Suggestion Web Application leverages intelligent algorithms to recommend personalized grocery items based o
products, recipes, and shopping lists. It integrates with a database of grocery items and uses recommendation algorithms to

A Smart Car Parking System built with the MERN stack (MongoDB, Express.js, React, and Node.js) provides an efficient,
user-friendly frontend interface, and Node.js for seamless, real-time data handling. Users can find available parking spots, r
volumes, accurate space management, and enhanced user convenience, streamlining the parking experience and maximizin
An E-commerce platform with POS Inventory, built using the MERN stack (MongoDB, Express.js, React, and Node.js), in
transactions, while Express.js handles backend API operations. React delivers a dynamic and responsive frontend interface
tracking, and facilitates smooth transactions, enhancing operational efficiency and providing a unified platform for both e-c
A Garbage Collection System developed in Node.js offers a real-time, scalable solution for managing waste collection and
services. Features include dynamic route adjustments based on real-time traffic and waste levels, automated notifications fo
enhances efficiency, reduces operational costs, and improves service delivery in waste management.
A Complaint Submission System using blockchain technology offers a secure and transparent platform for recording and m
its lifecycle. Users can submit complaints with verified timestamps and access a transparent history of all actions taken on t
and preventing fraudulent alterations.
A Gmail IMAP application provides a robust platform for managing and synchronizing email communications through the
synchronization of folders and email statuses. By utilizing IMAP’s capabilities, the application supports advanced features
consistent access to email data, regardless of device or location, while facilitating efficient email organization and managem
A Vaccine Supply Chain System using blockchain technology offers a secure and transparent solution for managing the dis
This transparency enables real-time tracking of vaccine batches, verification of their authenticity, and monitoring of temper
and efficiently delivered to their intended destinations while maintaining compliance with regulatory standards.
A Human Resource Management System (HRMS) offers a comprehensive solution for managing employee-related process
platform. It provides real-time access to employee records, facilitates efficient workflow automation, and supports data-driv
up-to-date management of human resources.
An Online Auction Application provides a digital platform for conducting real-time auctions where users can bid on items f
friendly interface, secure payment processing, and comprehensive item listings, the application ensures a smooth and engag
both buyers and sellers.
A Cargo Management System offers a comprehensive solution for tracking and managing the logistics of cargo transportati
automated scheduling, shipment notifications, and integration with various transportation modes and systems. By centralizi
while maintaining detailed records and compliance with regulatory requirements.
An Automated College Timetable System provides a streamlined, efficient solution for scheduling and managing academic
requirements. It offers real-time updates and conflict resolution, ensuring optimal timetable allocation and minimizing sche
synchronization with academic records, enhancing overall administrative efficiency and improving the academic experienc
A Career Guidance AI Chatbot provides a sophisticated, interactive platform for offering personalized career advice and gu
tailored recommendations on career paths, educational opportunities, and job search strategies, while continuously learning
make informed career decisions and navigate their professional development effectively.
The Disaster Alert and Crisis Relief System provides a comprehensive platform for managing and responding to emergenci
includes features for tracking disaster progress, coordinating relief efforts, and disseminating critical information through m
system enhances preparedness, optimizes resource allocation, and improves overall crisis management and relief operations
Farmer Harvest Connect is a MERN stack platform designed to streamline agricultural operations by connecting farmers w
integrates real-time features for booking and managing services, including vehicle rentals and labor, while providing a mark
interactions between farmers and service providers, ultimately supporting the agricultural community’s needs.
A Payroll Management System built with React.js offers a modern, user-friendly interface for managing employee payroll e
calculations, tax deductions, and benefits administration. Features include real-time payroll updates, detailed pay stubs, and
employees with timely and transparent payroll information.
Nutrient Recommendation System built with the MERN stack (MongoDB, Express.js, React, and Node.js) provides a comp
intuitive user interface, and Node.js for real-time data processing, the system delivers tailored nutritional guidance based on
overall health with a responsive, scalable solution.
The Event Marriage Hall Booking System built with the MERN stack (MongoDB, Express.js, React, and Node.js) provides
for handling backend services, and Node.js for real-time processing, the system allows users to browse available venues, ch
operational efficiency while ensuring smooth, secure management of marriage hall reservations.
The Online Driver Hiring Platform built with the MERN stack (MongoDB, Express.js, React, and Node.js) offers a compre
robust backend services, and Node.js for real-time data processing, the platform enables users to easily search for, book, an
ensuring a smooth and reliable service experience.
The Disaster Alert and Crisis Relief Response Coordination Platform, built with the MERN stack (MongoDB, Express.js, R
scalable data management, Express.js for robust backend services, and Node.js for real-time communication, the platform e
communication channels, enhancing overall crisis management and response effectiveness while ensuring streamlined coor
The Food Recipe Recommendation System, developed using the MERN stack (MongoDB, Express.js, React, and Node.js),
MongoDB provides flexible data storage for recipes and user profiles. Express.js manages backend operations, and Node.js
delivering tailored culinary recommendations and enhancing users’ cooking experiences through a seamless, scalable web a
The Lost & Found Finder, built with the MERN stack (MongoDB, Express.js, React, and Node.js), provides an efficient pla
and Node.js for real-time updates, the application allows users to easily post and search for lost or found items. Features inc
enhancing the recovery process and improving community engagement.
The PG Finder and Hostel Booking Management System, developed with the MERN stack (MongoDB, Express.js, React, a
availability, and making reservations. MongoDB handles flexible data storage for property details and user profiles, while E
process of finding and securing suitable accommodation while enhancing user experience and operational efficiency.
The Online POCSO Child Complaint Management System, built with the MERN stack (MongoDB, Express.js, React, and
friendly, responsive interface for submitting and tracking complaints, while MongoDB stores sensitive case data and user in
automated case handling, and streamlined coordination with authorities, enhancing the overall effectiveness and responsive
The Training Driving School Management System, developed with the MERN stack (MongoDB, Express.js, React, and No
schedules, while MongoDB offers flexible and scalable data storage for student records, instructor profiles, and vehicle man
automated reminders, performance tracking, and secure payment processing, ensuring a streamlined and effective managem

The Women Legal Assistance Advocate Finder App is an innovative platform designed to bridge the gap between women s
discrimination, and other gender-related legal issues. By leveraging a user-friendly interface and advanced search algorithm
with detailed profiles, practice areas, and client reviews, allowing users to make informed decisions about their legal repres
to accessibility and user-centric design, the Women Legal Assistance Advocate Finder App aims to enhance the legal empo

The Organ Donation App is a groundbreaking digital platform designed to simplify and enhance the process of organ donat
register as organ donors, manage their donation preferences, and access vital information about the organ donation process.
benefits and impact of organ donation, aiming to raise awareness and encourage more individuals to participate. Through a
efficiency and accessibility of organ transplantation.
The Electric Vehicle Recharge Bunk App is a state-of-the-art mobile application designed to streamline the electric vehicle
including availability, charging speeds, and pricing. Users can locate and navigate to the nearest recharge bunk, reserve cha
charging progress, and managing of user accounts. It also includes a community feature where users can rate and review ch
adoption of electric vehicles and contributes to a more sustainable future.

The eAyurvedic App is an innovative digital platform dedicated to providing personalized Ayurvedic solutions for a wide r
interface, users can input their health concerns and receive customized treatment plans, including herbal remedies, dietary s
treatments, and practices. Users benefit from expert consultations and educational content designed to enhance their unders
and promote holistic healing through personalized, natural solutions.

The Online SMART BUSINESS platform is a cutting-edge digital solution designed to streamline and enhance the operatio
supply chain, inventory, and sales processes. Retailers benefit from an intuitive interface that facilitates easy product select
performance analytics. Stockists can efficiently manage their bulk inventory, monitor stock levels, and ensure timely replen
and automation across these critical business functions, the Online SMART BUSINESS platform aims to enhance operation

The Child Safety Application is a cutting-edge mobile platform designed to enhance the safety and security of children in to
include real-time location tracking, geofencing alerts, and emergency contact management to ensure that children are safe a
Additionally, it offers educational resources and safety tips to help children understand and navigate potential risks. With it
environment for them to thrive.

The PG Locator app is a sophisticated digital solution crafted to simplify the search for paying guest (PG) accommodations
PG hostels and rental properties. Users can easily search and filter listings based on their preferences such as location, budg
managers. Additionally, users can read and leave reviews, enhancing the decision-making process with insights from previo
the PG Locator app aims to facilitate a smooth and efficient housing search, helping users find the perfect accommodation q

The eLearning platform for Skill Development and Learning is an advanced digital solution designed to provide a dynamic
Users can access a diverse catalog of interactive lessons, video tutorials, and practical exercises tailored to their individual l
includes tools for tracking progress, setting milestones, and receiving feedback from expert instructors. Through its intuitiv
integrating flexibility with cutting-edge educational methods, the platform supports lifelong learning and skill enhancement

The Ambulance & Police Application is a vital mobile platform developed to enhance emergency response and public safet
quickly and efficiently. Features include real-time tracking of emergency response units, allowing users to monitor the arriv
the user's location. Additionally, users can report incidents, share critical information with responders, and receive updates
emergency services, and ensure greater safety and support for individuals in urgent situations.

The Health Diet App is an innovative digital platform designed to support users in achieving their nutritional and wellness g
needs. Users can create personalized meal plans based on their health objectives, dietary preferences, and restrictions, with
fitness trackers to monitor overall health and activity levels. Additionally, users receive educational content about nutrition
lifestyle, fostering better eating habits and overall well-being.

The "Rescue Wings for Disaster" application is a crucial digital tool designed to enhance disaster response and managemen
responders, volunteers, and affected individuals, ensuring effective coordination during disaster scenarios. Users can report
evacuation routes, facilitating efficient resource allocation and response planning. Additionally, it features a database of em
app aims to improve the effectiveness of disaster relief operations, enhance public safety, and provide critical support durin

The Digital Vehicle Application is an advanced mobile platform designed to streamline vehicle management and maintenan
rotations, and other routine services, receive notifications for upcoming appointments, and access detailed service histories.
Digital Vehicle Application aims to enhance vehicle longevity, optimize maintenance schedules, and provide a convenient
The Bike Car Service Management app is a specialized platform designed to manage the service and repair needs of bikes a
scheduling system for regular maintenance, a history log for past services, and real-time updates on the progress of repairs.
vehicle owners and ensure timely and effective maintenance.
The Agro App is a digital platform tailored for farmers to access and manage government-aided schemes and agricultural re
receive updates on eligibility criteria and deadlines. The app also features educational content on best farming practices, we
securing financial assistance
The Employee Leave Management System is an efficient tool designed to streamline the process of managing employee lea
provides features to approve or reject leave requests, generate reports, and monitor leave trends. The app integrates with org
simplify leave administration and improve overall HR efficiency.
The Chatbot for Students is an AI-powered digital assistant designed to support students in their academic journey. It provi
institution. By offering a conversational interface, the chatbot aims to enhance student engagement, reduce the workload on

The Doctor-Patient Portal in CorePHP is a robust web-based application that facilitates secure and efficient communication
medical histories, and schedule follow-ups. The system includes features for electronic prescriptions, lab result managemen

The Clothes Recommendation System is a personalized shopping tool designed to enhance the online fashion experience. U
real-time recommendations, helping users discover new trends and find outfits that match their taste. The system also inclu
satisfaction and streamline the shopping experience.

The Automatic Time Table Creation app is a powerful scheduling tool designed to automate the process of creating and ma
optimized timetables that minimize conflicts and maximize efficiency. Features include drag-and-drop adjustments, real-tim

The Social Networking Website is an interactive online platform designed to connect individuals and foster community eng
website also includes tools for discovering new connections, managing privacy settings, and participating in discussions. B

The Online Voting System is a secure and efficient digital platform designed to facilitate remote voting processes for electi
integrity of the vote. Users can cast their votes from any location, view real-time voting results, and receive updates on the
Online Voting System aims to increase voter participation and streamline election management.
The Product Rating System is a sophisticated digital tool designed to capture and analyze consumer feedback for products.
system includes features for filtering reviews by criteria such as date, rating, and user demographics, helping potential buye
Rating System enhances transparency and supports both buyers and sellers in the marketplace.
The Online Cake Ordering System is a user-friendly digital platform designed to simplify the process of ordering cakes for
time tracking of orders, secure online payments, and customer reviews. It also offers integration with inventory managemen
efficient cake delivery services.
The Stock Management System is a comprehensive digital solution designed to optimize inventory control and streamline s
demand, and receive alerts for low inventory or overstock situations. The system includes tools for integrating with procure
Management System aims to improve operational efficiency and reduce costs.
The Social Networking Platform, designed to offer functionalities similar to Facebook, is a dynamic digital environment fo
events, and engage in discussions with their network. The platform also provides customization options for privacy settings
professional networking.
The Online Wedding Planner is a comprehensive digital tool designed to assist couples in organizing and managing their w
templates, checklists, and timeline reminders to ensure every aspect of the wedding is addressed. The platform also include
aims to simplify the process and enhance the overall wedding experience.
The Daily Expenses Management System is an intuitive digital tool designed to help users track and manage their daily spe
categorization based on user preferences. The system also offers financial insights and alerts for staying within budget, as w
planning and management.

The Library Management System is a digital platform designed to streamline library operations and enhance user experienc
history. The system provides administrative tools for managing inventory, generating reports, and handling user registration

The Online Birth Certificate System is a digital platform that simplifies the process of applying for and obtaining birth certi
the issuance process. It includes features for downloading and printing certificates, as well as receiving notifications on app
applicants and government agencies.

The Online GST Billing System is a digital solution designed to streamline the generation and management of GST-compli
templates, manage client details, and automate tax calculations. The system also offers reporting tools for tracking sales, ex

The Online Sports Store is a dynamic e-commerce platform designed to cater to sports enthusiasts by offering a wide range
The store features an intuitive search and filter system to help customers find specific items, along with secure payment opt
comprehensive and user-friendly shopping experience, the Online Sports Store aims to meet the needs of athletes and sport
The Zoo Management System is an integrated digital platform designed to streamline the management of zoo operations. It
behavioral observations. Additionally, it offers tools for staff management, visitor ticketing, and exhibit maintenance. With

The Alumni Management System is a digital platform designed to facilitate the management and engagement of an instituti
such as newsletters and announcements, and provides a portal for alumni to connect, network, and share opportunities. Add
Alumni Management System aims to enhance the relationship between institutions and their alumni.
The Online Pharmaceutical System is a comprehensive digital solution for managing pharmaceutical operations and provid
and access customer reviews. Features include secure online prescriptions, inventory management, and integration with pay
manage pharmaceutical needs, the Online Pharmaceutical System aims to improve accessibility and customer satisfaction.
The Online Bakery Shop System is a user-friendly e-commerce platform tailored for bakeries to sell their products online. U
processing, and delivery scheduling. Customers can view product descriptions, ingredients, and prices, as well as track thei
System aims to enhance customer experience and streamline bakery operations.
The Online Food Ordering System is a digital platform designed to simplify the process of ordering food from restaurants.
delivery scheduling. Customers can view detailed information about menu items, including ingredients and nutritional infor
convenient and efficient food ordering experience, the Online Food Ordering System aims to enhance customer satisfaction
The Company Visitor Management System is a digital tool designed to manage and track visitors to a corporate facility. It i
times, providing real-time notifications to relevant staff. Additionally, it supports reporting and analytics for monitoring vis
and efficient environment for managing corporate visits.
The E-Pass Management System is a digital platform designed to facilitate the issuance and management of electronic pass
codes or barcodes. The system includes features for tracking pass status, managing renewals, and generating reports on pas
simplify administrative processes and improve user convenience.
The Airlines Reservation System is a sophisticated digital platform designed to streamline the booking and management of
statuses, and processing payments securely. Additionally, it supports integration with airline databases for up-to-date inform
convenience and optimize flight management.
The Online Matrimonial Project is a PHP-based web application designed to facilitate matchmaking and matrimonial servic
communication tools, and advanced search filters. The system also supports secure data handling and privacy settings to pro
for matrimonial services, the Online Matrimonial Project aims to help individuals find compatible partners and build meani
The Bank Management System (PHP) is a comprehensive digital solution designed to handle various banking operations ef
histories. It supports secure authentication, ensuring data protection and transaction security. The system also includes adm
banking processes and improve overall efficiency in financial management.
The Online Gas Booking System is a digital platform that simplifies the process of booking and managing gas cylinder deli
order history, and making secure online payments. Additionally, it provides notifications for upcoming deliveries and main
suppliers.
The Tuition Communication System, built with PHP and MySQL, is designed to facilitate effective communication betwee
updates, and track academic progress through a centralized platform. The system supports user management, notifications,
streamline communication in a tutoring environment.

The Minimal News CMS Project Using PHP is a lightweight content management system designed for managing and publi
managing news articles and a front-end display for readers. Features include user authentication, content approval workflow

The platform for Listing Rescued Pets for Adoption is designed to connect rescued animals with potential adopters, facilita
photos, and adoption requirements. Users can search for pets based on criteria such as breed, age, and location, and submit
accessibility, the system aims to increase adoption rates and support animal welfare efforts.

The Events Management System for College Fests is designed to streamline the organization and management of campus e
attendance through an easy-to-use interface. The system supports secure access control, ensuring that event details and part

The Online Music Player is a digital platform that allows users to stream and manage their music collections online. It inclu
through music libraries. Additionally, it offers features for personalized recommendations, social sharing, and integrating w
The Online Course Registration System is a digital solution designed to simplify the process of enrolling in and managing e
payments. It also supports administrative functions such as course management, student records, and reporting. By offering

The Doctor Appointment System is a digital platform that facilitates the scheduling and management of medical appointme
provides a secure portal for managing patient information and appointment history. By offering a convenient and efficient w
The Laundry Management System is a digital tool designed to streamline laundry operations for both residential and comm
The system also provides tools for managing inventory, tracking service requests, and generating reports. By automating an

The Simple Task Manager Web App is a streamlined digital tool designed to help users organize and manage their daily tas
them as complete once finished. The app includes functionalities for setting reminders and notifications to keep users on tra

The Quiz Application is an interactive digital platform designed to create, manage, and take quizzes. It allows users to desig
application also supports user authentication, progress tracking, and analytics for performance assessment. By offering an e
The Universities Admission Process Online is a comprehensive digital platform designed to simplify the university admissi
check admission criteria, and receive updates on deadlines and requirements. The system includes tools for managing appli
for both students and universities.

The Advanced Online Booking System for Courier Service is a sophisticated platform designed to manage and streamline c
notifications, and payment processing. It supports integration with logistics and inventory management tools to optimize de

The "Eat Pizza and Enter Ingredients" System is an engaging digital tool that allows users to customize their pizza orders b
nutritional content. The system includes features for saving favorite combinations, placing orders online, and tracking deliv

The Chat Application made with PHP and MySQL is a real-time messaging platform designed for secure and efficient com
PHP for server-side functionality and MySQL for database management, the system ensures reliable performance and scala

The Attendance Management System with a layout inspired by Book My Show is designed to streamline the tracking and m
real-time tracking. The system includes tools for generating reports, managing student or employee profiles, and sending no

The Online Railway Reservation System is a digital platform designed to simplify the process of booking and managing rai
securely. It also provides real-time updates on train statuses and ticket booking history. By offering a comprehensive and us
The Course Multilingual Content Management System is a versatile platform designed to manage and deliver educational c
tools for managing user access, tracking course progress, and generating reports. By providing a multilingual environment,
The Application for Generating Question Papers is a digital tool designed to assist educators in creating and managing ques
random question sets, reviewing and editing papers, and printing or exporting final documents. By automating the question
The Phone Repair System, developed using PHP and MySQL, is a digital solution designed to streamline the management o
job ticket creation, parts inventory tracking, and invoicing. Users can log repair details, update job statuses, and generate re
efficiency and customer service in phone repair businesses.
The Mentor Allocation System is a digital platform designed to facilitate the assignment of mentors to mentees in education
administrators to oversee allocations, track progress, and manage feedback. Users can schedule meetings, communicate sec
support personal and professional development.

The Notes Management System is a digital tool designed to help users organize and manage their notes efficiently. It featur
and synchronize across multiple platforms. The system includes backup and recovery options to ensure data integrity. By o

The Schedule Cleaning Services System is designed to help students or service providers manage and schedule cleaning tas
with service providers. Users can view available time slots, request specific services, and provide feedback on completed ta

Social Spark is a social media platform developed using Core PHP, designed to facilitate online interactions and networkin
Users can engage with content through likes, comments, and shares, while administrators manage content, monitor activity,
The Art Gallery Management System is a digital solution designed to manage art galleries and exhibitions. It includes featu
online gallery views, reservation management, and event scheduling. By offering tools for efficient gallery operations and e
The Online Polling System, developed using PHP, is a digital tool designed to create and manage polls and surveys. It allow
ensure the integrity of poll results and provides tools for generating reports and visualizing data. By offering an easy-to-use
The Online Bus Reservation Site is a web-based platform designed to simplify the process of booking and managing bus tra
tools for managing reservations, tracking bus statuses, and generating reports. By offering a convenient and efficient solutio

The Online Notice Board is a digital platform designed to post and manage notices and announcements. Users can create, e
for new or updated posts. Administrators can manage user access and monitor notice board activity. By offering a centraliz

The Farm Management System is a comprehensive digital tool designed to streamline the management of agricultural opera
reporting on farm performance. Users can access real-time data, manage farm inputs, and analyze production metrics. By p

The Online Musical Instrument Shop in PHP is an e-commerce platform tailored for selling a diverse range of musical instr
reviews. The system features advanced search and filter options, secure online payments, and real-time inventory managem
aims to cater to musicians and enthusiasts efficiently.
The Jewellery Shop in PHP is an elegant online platform designed for showcasing and selling various types of jewelry, incl
order tracking, and customer reviews. Users can filter products by category, material, and price, and access personalized rec
Shop aims to attract and retain customers in the competitive jewelry market.
The Matrimonial System in PHP is a web application designed to facilitate matchmaking and matrimonial services. Users c
management, messaging, and privacy settings. It also supports advanced search algorithms and compatibility assessments t
relationships.

The Interview Management System in PHP is a digital tool designed to streamline the scheduling and management of job in
feedback forms. The system also supports interview rescheduling, candidate tracking, and reporting on interview metrics. B

The Hotel and Tourism Reservation System in PHP is a comprehensive platform designed to manage hotel bookings and to
payments, and providing booking confirmations. Additionally, it supports tour package bookings, itinerary management, an

The Smart Parking System in PHP is a digital solution designed to optimize parking management in urban and commercial
and receive notifications about parking status. The system also supports parking analytics and reporting for administrators.

The Insurance Management System is a comprehensive platform designed to handle various aspects of insurance operation
customer account management, automated notifications, and reporting tools for policy and claims data. By providing a cent
The Cinema Seat Reservation System in PHP is a digital platform designed to manage and streamline the process of reservi
payment processing. It also supports ticket cancellations and modifications, as well as promotional offers. By offering a con
The Invoicing System in PHP is a digital tool designed to automate and manage the invoicing process for businesses. It inc
The system supports online payment integration, invoice reminders, and overdue notifications. By streamlining the invoicin

The Responsive Blog Site in PHP is a web application designed to create and manage blog content with a focus on responsi
media integration, and content sharing. It is optimized for various devices and screen sizes, ensuring a seamless experience

The Traffic Offense Reporting System is a digital platform designed to streamline the process of reporting and managing tr
generation, notifications to law enforcement, and tracking of report statuses. It also includes features for reviewing and man
public safety.
The Patient Record Management System is a comprehensive platform designed to manage and organize patient health reco
records, allowing healthcare providers to view and update information as needed. It also features tools for managing prescri
processes.

The Campus Recruitment System is a digital solution designed to facilitate the recruitment process for educational institutio
application tracking, and interview scheduling. It supports communication between recruiters and candidates, as well as rep
The Sports Event Management System is a digital platform designed to manage and organize sports events and tournament
can view event schedules, participate in discussions, and access event updates. By providing tools for efficient event organi
The Faculty Profile Management System is a digital solution designed to manage and maintain detailed profiles of faculty m
supports profile searches, faculty directory management, and reporting on faculty activities. By offering a centralized platfo

The Social Media App Like Facebook is a comprehensive social networking platform designed for users to connect, share,
It also includes features for user engagement, such as likes, comments, and shares, as well as privacy settings and content m

The Dynamic Portfolio Website in PHP is a web application designed for individuals or businesses to showcase their work
present their portfolios in a visually appealing and professional manner. Features include content management, media integ
online presence.
The PHP-Based Public Complaints Portal is a digital platform designed to enable citizens to report and track public grievan
communication with relevant authorities. It also supports complaint categorization, prioritization, and reporting. By offerin
The Sentiment Analysis Enhanced CRM System in PHP is a customer relationship management platform augmented with s
management, interaction history, and sentiment analysis of customer communications. The system provides insights into cu
business decision-making.

The PHP-Based Gym and Fitness Club Manager is a digital platform designed to manage the operations of gyms and fitnes
classes and personal training sessions. It also includes tools for billing, reporting, and managing gym equipment and staff. B

The PHP Online Blood Bank Management System is a comprehensive platform designed to streamline the management of
inventory, processing requests from hospitals, and generating reports on blood stock and donor activity. It supports secure d
improve blood availability.
The Online Lab Report System in PHP is a digital tool designed to manage and deliver laboratory test results. It allows med
tracking of test history. It supports automated notifications for report availability and provides options for generating and pr
facilities.

The Driving School Management Solution in PHP is a web-based platform designed to manage the operations of driving sc
progress tracking for students. Additionally, it provides tools for generating reports on student performance and financials.

The Automated Loan Verification System in PHP is a digital platform designed to streamline the loan verification process.
managing document submissions. It supports automated credit checks, risk assessment, and approval workflows. Additiona
making in lending operations.

The Automated Faculty Evaluation Platform in PHP is a web-based solution designed to facilitate the evaluation of faculty
system includes features for survey management, data analysis, and reporting. It supports automated reminders and secure d

The PHP-Based Operational Schedule Management System is a digital tool designed to manage and organize operational sc
notifications, and reporting on schedule adherence and performance. Users can view and adjust schedules in real-time, man
efficiency.
The EliteSalon Advanced Management System is a comprehensive platform designed for managing salon operations. It inc
marketing and promotions, client feedback, and reporting on salon performance. By offering an integrated solution for salo

The EcoCharge Hub is an advanced management system for electric vehicle (EV) recharge stations. It includes features for
consumption reporting. It also provides tools for integrating with EV infrastructure and managing maintenance schedules. B

The StudentSuccess Advanced College Results Management System is designed to manage and track academic performanc
automated report generation, and performance tracking. Additionally, it provides tools for managing student enrollment, co
administration.
The StudentSeminarPro Advanced Hall Booking System is a digital platform designed to manage the booking and scheduli
booking, conflict resolution, and automated notifications for booking confirmations and changes. Additionally, it provides t
optimize facility usage.
The Metaverse, which is emerging as the next-generation (NextG) Internet, offers an immersive 3D virtual world in which
inherited from its predecessor as well as various new emerging threats. Furthermore, the decentralized nature of the Metave
devices. In this article, we aim to analyze the security aspect of the Metaverse thoroughly with special discussions of soluti
ML. Next, we develop a decentralized collaborative intrusion detection system (CIDS) based on blockchain and federated l
approaches, which may not be effective in protecting the Metaverse with increasingly sophisticated attacks. Finally, we out

In the era of deep learning, federated learning (FL) presents a promising approach that allows multi-institutional data owne
leading to a single point of failure. This makes the system vulnerable to malicious attacks when dealing with dishonest clien
mechanism and a reward-and-slash mechanism, which are powered by on-chain smart contracts, to detect and deter malicio
behaviors.

The convergence of blockchain, Metaverse, and non-fungible tokens (NFTs) brings transformative digital opportunities alo
in this paper. Through user work-offloading, we optimize data tasks, user connection parameters, and server computing freq
the trust-cost ratio (TCR), a pivotal measure combining trust scores from users' resources and server history with delay and
semidefinite relaxation (SDR), the Hungarian method, and a novel fractional programming technique from a recent IEEE JS
order to be solved by SDR and the Hungarian algorithm. Extensive simulations validate the DASHF algorithm's efficacy, re

This paper introduces an innovative approach to designing a user-based Heating, Ventilation, and Air-Conditioning (HVAC
excessive use, users can modify their behavior to pass to a less expensive and more virtuous consumption class. To this aim
solved by a Model Predictive Control (MPC) strategy integrated with a Long Short-Term Memory network as a predictive
located in a more virtuous consumption class. A case study conducted within an energy district in Bari (Italy) shows how th
of efficiently managing HVAC systems in smart districts through a novel blockchain-based framework and an optimization
penalize inefficient utilization. For practitioners, this strategy translates to a granular level of energy management that not o
usage. At the same time, adopting MPC with Long Short-Term Memory Networks offers accurate forecasts and adjustment

Cloud computing has completely revolutionized the concept of computing by providing users with always-accessible resou
required whenever a user switches providers, is one of the most common issues the users encounter. Due to smartphones’ li
cloud provider. Additionally, the user must remember numerous tokens and passwords for different applications. In many i
because cloud service providers manage and control all data and resources stored in the cloud. However, cloud users would
binding agreements and anonymous identities to address this problem. Based on a binding contract and admission control p
and classify anonymity in the cloud by conducting various pre-processing techniques, feature selection, and dimensionality

Mobile AI-Generated Content (AIGC) has achieved great attention in unleashing the power of generative AI and scaling th
clients and MASPs in public mobile networks, pertaining to three key mechanisms, namely MASP selection, payment sche
ProSecutor. Specifically, by roll-up and layer-2 channels, ProSecutor forms a two-layer architecture, realizing tamper-proof
OS
2
?
A
) framework, which effectively evaluates the AIGC services by fusing the objective service quality with the reputation-base
OS
2
?
A
on ProSecutor, firstly, the MASP selection can be realized by sorting the reputation. Afterward, the contract theory is adopt
that ProSecutor achieves 12.5
×
throughput and saves 67.5% storage resources compared with BlockEmulator. Moreover, the effectiveness and efficiency o
The employment of blockchain technology in electronic voting (e-voting) systems is attracting significant attention due to i
The study investigates a range of key research concerns, including the benefits, challenges, and impacts of such systems, to
principles to select and categorize scientific papers and reviewing the technology used in these in terms of the above key co
verifiability, efficiency, trustworthiness, and auditability receive significant attention, they are not the primary focus. We ob
discussed as the aforementioned key benefits in the proposed solutions for blockchain-based e-voting systems, whereas the
crucial aspect of scalability needs attention

Bridge health monitoring becomes crucial with the deployment of IoT sensors. The challenge lies in securely storing vast a
blockchain for monitoring bridges. One of the emerging blockchains, EOSIO is used because of its exceptional scaling capa
observe meaningful patterns in the data. Smart contracts of EOSIO are used in implementation because of their efficiency,
blockchain, as well as useful predictions based on the NI. Performance analysis uses real-time data collected from IoT sens
BIONIB under varying numbers of sensors and various numbers of participating blockchain nodes is observed. We observe
a significant concern in bridge health applications, the results demonstrate that BIONIB has high throughput, parallel proce

Intelligent Transportation Systems (ITS) supported by smart vehicles have revolutionized modern transportation, offering a
channels among various entities, including smart vehicles, roadside infrastructure, and fleet management systems, introduc
for smart vehicles-enabled ITS (BASF-ITS), which ensures data protection both during transit and while stored on cloud se
(PUF), to design authenticated key agreement schemes. The inclusion of PUF significantly enhances the system’s resistanc
decentralization of the blockchain, BASF-ITS effectively safeguards data at rest, providing an additional layer of security. W
a comparative analysis with contemporary competing schemes, BASF-ITS emerges as a promising approach, offering supe
technology, showcasing the computational time versus the “transactions per block” and the “number of mined blocks

Material data forms the foundation of the Industrial Internet of Things (IIoT). The rapid advancement of big data technolog
material big data platform is expanding its data scale and facing an increasing demand for sharing in light of the continuous
challenges, this article focuses on the National Materials Genetic Engineering Discrete Data Exchange Platform (MGED). I
Additionally, a verifiable retrieval scheme based on a two-layer index structure of bitmap and MPT tree is proposed to enha
Through integrating blockchain technology and adopting a novel retrieval scheme, the article presents a comprehensive app
to the efficient and accurate retrieval of heterogeneous data.

Integrating blockchain technology with the Internet of Things (IoT) facilitates seamless interaction between IoT devices an
difficult to adapt existing access control mechanisms to the dynamic and context-dependent nature of IoT environments, ne
access control (SC-CAAC) scheme for BIoT systems. It utilizes context-aware access control models that consider contextu
access control policies and manage access permissions, ensuring that sensitive data and resources are accessible only to aut
need for a central authority to record and audit access control policies and decisions and promoting accountability and trust

In recent years, Decentralized Finance (DeFi) grows rapidly due to the development of blockchain technology and smart co
the most notorious examples is the ``Rug Pull" scam. This type of cryptocurrency scam occurs when the developer of a par
losses. In this work, we manually collected and analyzed 103 real-world rug pull events, categorizing them based on their s
without utilizing malicious functions). Based on the analysis of rug pull events, we propose CRPWarner (short for Contract
related to rug pull events and achieved a 91.8% precision, 85.9% recall and 88.7% F1-score. Additionally, when evaluating
experiment reach 84.9%.

Currently, smart contract vulnerabilities (SCVs) have emerged as a major factor threatening the transaction security of bloc
vulnerability patterns by fitting vulnerability labels. It is a pity that they disregard the correlation between contracts, failing
level.
To tackle this problem, we propose a novel Contrastive Learning Enhanced Automated Recognition Approach for Smart Co
labels based on the relationships between contracts to guide the training process of the CL model. Finally, it combines the c
the-art baseline methods. We show that Clear achieves (1) optimal performance over all baseline methods; (2) 9.73%-39.99
This article aims to study intrusion attacks and then develop a novel cyberattack detection framework to detect cyberattacks
blockchain network will serve two purposes, i.e., to generate the real traffic data (including both normal data and attack dat
that is synthesized in a laboratory for cyberattacks in a blockchain network. We then propose a novel collaborative learning
knowledge from data using the Deep Belief Network, and then share the knowledge learned from its data with other blockc
conventional centralized learning solutions. Such a framework can also avoid the risk of exposing local data's privacy as we
98.6% in detecting attacks

Introducing blockchain into Federated Learning (FL) to build a trusted edge computing environment for transmission and le
in handling large-scale FL tasks, especially on Internet of Things (IoT) devices, due to their substantial resource consumpti
the IoT network into multiple shards within the subchain layer, effectively reducing the scale of information exchange, and
integrate deeply with blockchain technology, and a modified DAG consensus mechanism is designed to mitigate distortion
deployed. Extensive experiments demonstrate that ChainFL significantly surpasses conventional FL systems, showing up to

Medical healthcare centers are envisioned as a promising paradigm to handle vast data for various disease diagnoses using
hospitals (nodes) train and share encrypted federated models, solves the issue of data leakage and unites resources of small
preservation of privacy and security. The proposed model has been trained on the NIH Chest Ray dataset (112 120 X-Ray i
empirical tests against leading cyber threats to evaluate its robustness. With resilience metrics consistently nearing 87% aga
practical implementation of blockchain-empowered FL with such data and several diseases, including multiple disease coex

With the rapid development of machine learning and a growing concern for data privacy, federated learning has become a f
Blockchain-based Federated Learning Model (PPBFL) to enhance the security of federated learning and encourage active p
Within the blockchain, we introduce a Proof of Training Work (PoTW) consensus algorithm tailored for federated learning
adaptive differential privacy algorithm is simultaneously applied to local and global models. This safeguards the privacy of
resulting from the combination of numerous local models. The possibility of security degradation is derived from the comp
mix transactions mechanism utilizing ring signature technology to better protect the identity privacy of local training clients

Federated learning (FL) is a machine learning paradigm, which enables multiple and decentralized clients to collaboratively
aggregator, which forms cohorts of clients honestly. However, a malicious aggregator, in reality, could abandon and replace
malicious aggregator during the training model aggregation process. To guarantee the correct aggregation results, the aggre
handle the proof in a zero-knowledge way, where miners (i.e., the participants validating and maintaining the blockchain da
FL, without modifying the underlying FL network structure or heavily compromising the training speed.

In the era of data-driven healthcare, the amalgamation of blockchain and federated learning (FL) introduces a paradigm shi
sharing, aiming to strike a balance between data utility and privacy. FL, a decentralized machine learning paradigm, enable
ecosystem fostering trust, security, and data integrity. This article elucidates the technical foundations of FL and blockchain
while granting healthcare providers and researchers access to diversified data sets, ultimately leading to more accurate mod
of FL and blockchain envisions a healthcare ecosystem that prioritizes individual privacy and propels advancements in med

Anomaly detection in the industrial internet of things (IIoT) devices is significant due to its fundamental role in protecting m
trained, thus improving the performance of the model. However, due to the sensitivity and privacy of IIoT data, it is also di
side structure and federated learning. We store the global model on the main-chain while the side-chain records the hash va
nodes participating in the current federated learning training can get the latest global model, so as to encourage the nodes to
the test dataset to resist the poisoning attack of the models. We also use the local differential privacy (LDP) algorithm to pr
the users add a lot of noise to their local models.

We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen

The configuration of security systems for communication protection, such as VPNs, is traditionally performed manually by
Moreover, even when a solution is computed correctly, sub-optimizations that may afflict the performance of the configure
proposes an automatic approach to compute the configuration of VPN systems. Both the allocation scheme of VPN systems
formal correctness-by-construction and optimization of the result. A framework implementing this approach has been devel
This article is concerned with the secure distributed economic dispatch (DED) problem of microgrids. A quantized distribu
generators (DGs) in order to meet the total load demand at the lowest generation cost under the DG capacity limits while en
the effects of quantization errors can be eliminated. Next, utilizing matrix norm analysis and mathematical induction, a suff
using sign transmissions). Moreover, an encryption–decryption scheme is developed based on quantized outputs, which ens
are confirmed through a simulated example

Mobile edge computing (MEC) has emerged as a solution to address the demands of computation-intensive network service
vehicles (UAVs) have been employed to assist MEC. This paper investigates the task offloading problem in a UAV-assisted
optimization of UAVs' trajectory design, binary offloading decision, computation resources allocation, and communication
space of this problem, we propose a novel deep reinforcement learning (DRL) algorithm based on the latent space to solve

The Internet of Things (IoT) is being prominently used in smart cities and a wide range of applications in society. The bene
since security solutions designed for general information/operational technology systems may not work as well in an enviro
employed i.e., Deep Belief Network (DBN) and Convolutional Neural Network (CNN), considered hybrid classifiers, to cre
paper also aims to present a new hybrid optimization algorithm called “Seagull Adapted Elephant Herding Optimization” (S
benign. Using sensitivity, precision, accuracy, and specificity, two datasets were compared. In every performance metric, th

Deep Reinforcement Learning (DRL) algorithms have recently made significant strides in improving network performance
paramount importance. Taking this problem into account, we propose a safe learning-based load balancing algorithm for So
into feasible ones during both training and testing, and it guides learning towards safe policies. We successfully implement
approach delivers near-optimal Quality-of-Service (QoS performance in terms of end-to-end delay while respecting safety r
Deterministic Policy Gradient (DDPG) when both are combined with a CBF for safe load balancing.

Vertical Federated Learning (VFL) is a trending collaborative machine learning model training solution. Existing industrial
remains a risk in VFL due to the correlations between intermediate representations and raw data. Neural networks can accu
Our work shows that hashing is a promising solution to counter data reconstruction attacks. The one-way nature of hashing
address these issues, we propose HashVFL, which integrates hashing and simultaneously achieves learnability, bit balance,
Experimental results indicate that HashVFL effectively maintains task performance while defending against data reconstruc
into the potential applications of HashVFL

Major Depression Disorder (MDD) is a common yet destructive mental disorder that affects millions of people worldwide.
diagnosis. However, there are still some challenges in data quality and data size of EEG: (1) A large amount of noise is inev
model training. Both of the challenges cause the overfitting problem, especially for deep learning methods. In this paper, w
designing the Forward Diffusion Noisy Training Module. Then we increase the size and diversity of data to help the model
comprehensive experiments to test the overall performance and each module's effectiveness. The framework was validated

Machine learning poses severe privacy concerns as it has been shown that the learned models can reveal sensitive informati
privacy leakage of machine learning models. Such privacy effects are often measured by membership inference attacks (MI
memorization, we find that previously deployed MIAs produce misleading results as they are less likely to identify samples
evaluation. Through extensive experiments, we unveil several findings about the connections between three essential prope
the previous results. Moreover, there is not necessarily a trade-off between adversarial robustness and privacy as stronger a

Software-defined Network (SDN), presented to be a novel architecture of network because of its separation of data plane an
majority of SDN, leads to the widely used definition of the communication between the controller and the switch resulting
general implementations or device limitations. Despite the common vulnerabilities, the universal standard mechanisms of b
SDN components, their key functions, and communications along with the malicious operations that could be executed by m
from the common vulnerabilities of the SDN system reports the potential attack paths each of which shows an attack proces
practicality of the 2 new attacks
The number of people with kidney disease rises every day for many reasons. Many existing machine-learning-enabled mec
schemes can be used to develop the best delay scheme. The scheme must optimize both the internal and external states of re
consumers’ kidney disease image processing. The main relationship between IoT consumers and kidney image is that the d
federated learning datasets for training and testing and run them on different fog and cloud nodes. AFRLS decides the sche
other machine learning methods used in fog cloud networks. The AFRLS improved the delay among nodes by 55%, the del

In the emerging Web 3.0 applications for mass customized and personalized manufacturing, smart mobile resources need to
movement direction of smart mobile resources to meet the high requirements for communication rate and reliability in high
introduces an edge-cloud collaboration framework for smart factories to support autonomous wireless access point selection
leverage multiple antennas and movement direction to address the unstable connection problem. Third, a centralized-trainin
input information of the next interaction objects for mobile resources. Simulation results show that the proposed MARL sch

In recent years, cloud computing has been widely used. Cloud computing refers to the centralized computing resources, use
for individual users, but also for enterprise users. By purchasing a cloud server, users do not have to buy a large number of
cloud service providers in China are Ali Cloud, Baidu Cloud, Huawei Cloud and so on. Therefore, this paper proposes an in
such as low resource utilization and unbalanced load in the cloud environment, this study proposes a comprehensive solutio
computing resource management.Rational allocation of resources plays a crucial role in cloud computing. In the resource a
resources at a specific time.

Workflow Scheduling is a huge challenge in cloud paradigm as many number of workflows dynamically generated from va
Virtual Machine i.e. with low processing capacity which leads to delay in executing workflows and it results in increase of
using Deep reinforcement Learning. Initially, priorities of all workflows calculated based on their dependencies and then ca
schedule tasks by considering both priorities of tasks and VMs. Extensive simulations carried out on workflowsim by consi
Deadline, Cat Swarm Optimization, Ant Colony Optimization. Results revealed that our proposed MOPDSWRL outperform

This paper considers multiple unmanned aerial vehicles (UAVs) to assist sensing data transmissions from the ground users
data to the remote BS. The GUs frst backscatter their data to the UAVs and then all UAVs forward data to the BS by the no
a multi-stage stochastic optimization problem to minimize the long-term time-averaged age-of-information (AoI) by jointly
systems, and then propose the AoI-aware sensing scheduling and trajectory optimization (AoI-STO) algorithm. This allows
UAVs’ beamforming, and mobility control strategies are updated by
using the block coordinate descent (BCD) method according to the instant GUs’ AoI statuses. Simulation results reveal that
baseline schemes.

It is anticipated that integrated sensing and communication (ISAC) will be a key new technology in wireless communicatio
coexistence system with a STAR-RIS to improve communication performance, suppress mutual interference, and provide f
feasible rates at the radar and communication receiver side in closed forms, based on the realistic conditions of correlated f
simultaneously optimise the amplitudes and phase shifts of the STAR-RIS through a projected gradient ascent algorithm (P
compared to reflecting-only RIS, this feature is especially helpful because a STARRIS has twice as many variables, which
Additionally, a benchmark full instantaneous CSI (ICSI) based design is shown and demonstrated to have a larger overhead

This proposed system investigates a new approach to indoor and urban location tracking for wireless devices and ways to tr
tracking that leverages existing infrastructure (cell towers and Wi-Fi) instead of GPS. Protect user privacy in such a system
advantages indoors but raises privacy concerns since anyone with access to the system could potentially track users.

Automatic modulation classification (AMC) is a crucial technique for the design of intelligent transceivers and has received
complexity. However, these methods are highly sensitive to the distribution shifts of the received signal caused by the varia
frequency offset (CFO), phase offset (PO) and additive noise. To solve this problem, this paper proposes a novel FB metho
unseen synthetic channels in OFDM systems. Specifically, we first propose the axisymmetric mapping-based self-circulant
Subsequently, we derive
the EVM features by analyzing the matched error vectors between the generated NNSQ sequence and the predefined NNSQ
various channel conditions are sent to the multi-class support vector machine (SVM) classifiers for training and testing. Tw
demonstrate that 1) the proposed method exhibits impressive robustness and generalization when dealing with unseen synth
This paper studies a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)-assisted wire
(SE) and energy efficiency (EE) in this system, a multi-objective optimization problem (MOOP) is formulated to maximize
the maximum transmit power of the BS and the minimum harvested energy of users. To tackle this MOOP, we propose a M
classic DDPG and genetic algorithms in terms of EE. Besides, via simulation results, it is illustrated that Meta-DDPG reach

Integrated sensing and communication (ISAC) is envisioned as a key pillar for enabling the upcoming sixth generation (6G
framework to explore the collaboration among multiple users for environmental sensing. Specifically, multiple users can se
capability of the leader node because it requires the leader node to process the signals sent by all the users. To this end, we
leader node and improving the robustness of sensing. This way, multiple users can cooperatively sense a target by exploitin
performance metric and propose a beamforming design for the proposed network ISAC scheme to maximize the networked
algorithms.

For most spectrum sensing applications, deep learning (DL) yields state-of-the-art performance, but it is susceptible to adve
specifically attempts to reduce the accuracy of the trespasser while ensuring that the intended recipient may still reliably rec
adversarial examples, and first claimed that the imperceptibility of adversarial examples in the field of image classification
and limited the adversarial perturbation to a small frequency range, making it impervious to filtering. In addition, we establ
edge DL-based attackers while reducing the loss of communication performance.

Although the underwater optical communication system (UWOC) plays an important role in many marine applications, the
great challenges in a long or turbid water channel. The Orthogonal Frequency Division Multiplexing (OFDM) and the spac
systems to improve spectral efficiency and data transmission reliability. On these foundations, a multi-input multi-output (M
requirement. In experiments, two sets of 450 nm blue laser diodes (LDs) and PIN photodiodes are selected as light sources
using an Alamouti coding for its anti-interference ability. The receiving plane is rotated to simulate the various alignment s
single-output OFDM (SISO-OFDM) are compared in tap water and turbid water. The results show that the spatial diversity
maximum detection angle range is 92% and 112% higher than the SISO system, respectively.

Due to its strong ?exibility, easy deployment and extensive connectivity, unmanned aerial vehicle (UAV) swarm has been w
infrastructures are no longer available. Within a UAV swarm, the design of routing protocol is one of the most challenging
the UAV nodes move randomly. In the context of mission-oriented scenarios, such as emergency communication in disaste
planning. Disregarding trajectory information from the application layer may result in routing protocols struggling to adapt
an effcient trajectory-based optimized routing protocol (TORP) for mission-oriented UAV swarm. Firstly, we model the pa
formulated problem is a binary linear programming (BLP) problem which is intractable to solve. Firstly, we propose a mod
simulation results demonstrate that our algorithm can make effective routing
selections in dynamic UAV network, thereby improving the system performance in terms of packet delivery ratio, end-toen

In this work, we investigate the joint visibility region (VR) detection and channel estimation (CE) problem for extremely la
on the statistical characteristics of channels in the spatial or delay domain, we propose an approach that simultaneously exp
regarding the visibility of antennas is obtained through a VR detection-oriented message passing (VRDOMP) scheme, whic
channel employing the belief-based orthogonal matching pursuit (BB-OMP) method. Simulations show that the proposed a

The effciency of the broadcast network is impacted by the different types of services that may be transmitted over it. Globa
Network (MBSFN) is typically used for global service transmission while existing literature extensively discusses schemes
services are made, leading operators to scale down to either Single Cell-Point to Multipoint (SCPtM) or Multi-Frequency N
transmitting hyper-local services without SFN gain. Our proposed Local and Hyper-Local Services (LHS) transmission sch
their corresponding radio link channel quality to schedule single or multi-resolution, local or hyper-local services within a t
transmitting multi-resolution multimedia content to address the problem of heterogeneity amongst the multicast group users
scheme also employs macro-diversity combining with optimal HM parameters for each gNB catering to a local service area

Detection of cyber-attacks in smart power distribution grids with unbalanced configurations poses challenges due to the inh
unbalanced power distribution grids integrated with DERs, i.e., PV systems and wind generation. The advantage of the prop
approach, it is tested on IEEE 13-bus and 123-bus systems with historical meteorological data (wind speed, ambient temper
unsupervised learning methods verifies its superior performance in detecting cyber-attacks in unbalanced power distribution
The domain name system (DNS) plays a crucial role in network communications, critical industrial systems (CIS), and SCA
network traffic as DoH or NonDoH. These can be malevolent, innocuous, or zero-day attacks. The suggested technique use
model achieved 99.28% accuracy and precision, 99.75% recall, and an AUC of 0.9975 with low training and testing time o
SMOTE approach for data balance. The suggested scheme's reliability was validated by evaluating an industrial control sys
coefficient (MCC), verifying its applicability

Big data has the ability to open up innovative and ground-breaking prospects for the electrical grid,
which also supports to obtain a variety of technological, social, and financial benefits. There is an
unprecedented amount of heterogeneous big data as a consequence of the growth of power grid technologies,
along with data processing and advanced tools. The main obstacles in turning the heterogeneous large dataset
into useful results are computational burden and information security. The original contribution of this paper is
to develop a new big data framework for detecting various intrusions from the smart grid systems with the use
of AI mechanisms. Here, an AdaBelief Exponential Feature Selection (AEFS) technique is used to efficiently
handle the input huge datasets from the smart grid for boosting security. Then, a Kernel based Extreme Neural
Network (KENN) technique is used to anticipate security vulnerabilities more effectively . In this process,
CICIDS-2017 was taken from dataset repository. Then, we have to implement the pre-processing, data splitting
and classification. Finally, the experimental results shows that the performance metrics such
as accuracy, precision and recall.

Power electronic systems (PES) face significant threats from various data availability and integrity attacks, significantly aff
complex cybersecurity operational platform with significant room for incremental extensions for mitigation against future t
into the sampling process for distributed energy resources (DERs). This unified approach concurrently compensates for the
Freshness, and Relevance to ensure resilient dynamic performance. Hence, the proposed scheme promises a generalized rou
California Edison (SCE) 47-bus network, using OPAL-RT under diverse operating conditions, underscores its robustness, m

In the age of the Internet, people's lives are

increasingly dependent on today's network technology.
Maintaining network integrity and protecting the legitimate
interests of users is at the heart of network construction. Threat
detection is an important part of a complete and effective defense
system. How to effectively detect unknown threats is one of the
concerns of network protection. Currently, network threat
detection is usually based on rules and traditional machine
learning methods, which create artificial rules or extract common
spatiotemporal features, which cannot be applied to large-scale
data applications, and the emergence of unknown risks causes the
detection accuracy of the original model to decline. With this in
mind, this paper uses deep learning for advanced threat detection
to improve protective measures in the financial industry. Many
network researchers have shifted their focus to exception-based
intrusion detection techniques. The detection technology mainly
uses statistical machine learning methods - collecting normal
program and network behavior data, extracting multidimensional
features, and training decision machine learning models on this
basis (commonly used include naive Bayes, decision trees, support
vector machines, random forests, etc.).
Applying large language models (LLMs) to modern power systems presents a promising avenue for enhancing
decision-making and operational efficiency. However, this action
may also incur potential security threats, which have not been
fully recognized so far. To this end, this article analyzes potential threats incurred by applying LLMs to power systems,
emphasizing the need for urgent research and development of
countermeasures.

Supervisory Control and Data Acquisition (SCADA)

systems are vulnerable to traditional cyber-attacks, such as manin-the-middle, denial of service, eavesdropping, and masque
attacks, as well as future attacks based on Grover’s and Shor’s algorithm implemented in quantum hardware. This paper pro
a quantum-robust scheme based on entanglement and supersingular isogeny-based cryptography. The scheme employs a m
shared secret keys, also authenticating BBM92, a quantum key
distribution protocol to generate a symmetric key. The paper uses
ASCON-128 and SHA-3 to encrypt and authenticate messages,
and provides a comparative analysis of two entanglement-based
quantum key distribution protocols. The proposed scheme is
compared to the current SCADA standard, AGA-12, and is
shown to provide confidentiality, integrity, intrusion resistance,
message authentication, and scalability. The randomness of key
pairs generated by our algorithm and RSA key pairs is 87.5%
and 84.37%, respectively, addressing confidentiality and integrity.
Using the BBM92 protocol, our proposed algorithm detects the
presence of an adversary by generating an average error rate of
26.07% and information leakage of 76.01%. AGA-12 relies on
SHA-1 hash function that Google has cracked recently. However,
our algorithm includes SHA-3, a collision and quantum-resistant
hash that provides message authentication.

As smart grids (SGs) increasingly rely on advanced technologies like sensors and communication systems for efficient ener
resilience of modern energy systems. While extensive research has been conducted, a comprehensive exploration of proacti
survey begins with an overview of related works and our distinct contributions, followed by an examination of SG infrastru
taxonomy of DL approaches, highlighting their roles and relevance in the proactive security of SG. Subsequently, we analy
overview of benchmark data sets used in this domain to substantiate the discourse. This is followed by a critical discussion
outlook on future developments in this key field.

Subsynchronous resonance (SSR) is among the most severe instability conditions that may happen when grid-tied inverter-
instability that could spread to a larger area. Such risks make the subsynchronous stability of permanent magnet synchronou
which have high energy output and less maintenance. Considering the major causes and different damping controls for SSR
smartly craft cyber attacks can successfully degrade SSR damping, trigger an SSR, and even destabilize the power grid.

Collapse

Consumer Electronics (CEs) are smart devices using IoT for connectivity. They’re susceptible to attacks like DoS, DDoS, a
causing vehicle failures. Existing ML/DL based IDS have high classification accuracy and robustness in traditional internet
these intrusion detection algorithms with other algorithms are not sufficiently comprehensive to evaluate their performance
hybrid feature selection model based on chi-square test and information gain combined Ig-Chi, which effectively reduces th
on the data after feature selection. The experiments on four public data sets demonstrate that this method surpasses six ML/

With the rapid advancement of vehicle connectivity and intelligent technologies, an increasing number of vehicles are now
witnessed a rise in incidents involving various network attacks, such as denial of service (DoS), fuzzy attacks, and gear atta
filter. It first utilizes the cuckoo filter to establish two lists (a normal list and an intrusion list) based on the labeled dataset u
BERT-based model. The ECF-IDS is experimentally validated using the CHD and can-train-and-test dataset, demonstrating
vehicle environment testing on the ECF-IDS model, and its detection performance proved to be excellent.
Distributed Denial of Service (DDoS) attacks pose a significant threat to the stability and reliability of online systems. Effe
capabilities of Deep Residual Neural Networks (ResNets) coupled with synthetic oversampling techniques. Because of the
Minority Over-sampling Technique (SMOTE) to the CICIDS dataset, we balance the representation of benign and maliciou
Experimental results on a real-world dataset demonstrate that our approach achieves an accuracy of 99.98%, significantly o

Distributed Denial of Service (DDoS) attacks pose a significant threat to the stability and reliability of online systems. Effe
capabilities of Deep Residual Neural Networks (ResNets) coupled with synthetic oversampling techniques. Because of the
Minority Over-sampling Technique (SMOTE) to the CICIDS dataset, we balance the representation of benign and maliciou
Experimental results on a real-world dataset demonstrate that our approach achieves an accuracy of 99.98%, significantly o

In the era of deep learning, federated learning (FL) presents a promising approach that allows multi-institutional data owne
leading to a single point of failure. This makes the system vulnerable to malicious attacks when dealing with dishonest clien
mechanism and a reward-and-slash mechanism, which are powered by on-chain smart contracts, to detect and deter malicio
behaviors

Recent years, the successful application of block-chain in cryptocurrency has attracted a lot of attention, but it has also led t
such as high complexity, poor scalability, and high latency. In this article, we propose a novel framework named phishing d
ego-graphs centered on labeled accounts. Then we propose a feature augmentation strategy based on structure features, tran
updated node features in descending order and then taking the mean value of the top n to obtain the graph representation, w
time, our framework has the advantages of lower complexity, better scalability, and higher efficiency, which detects phishin

Understanding the modus operandi of adversaries aids organizations to employ efficient defensive strategies and share intel
explained in the sentences of the threat report and convert it into a structured format. This research introduces a methodolog
state-of-the-art natural language model to augment sentences for minority class TTPs and refine pinpointing the TTPs in thr
39
,
296
sentence samples and a
149 real-world cyber threat intelligence report-to-TTP dataset. Further, we evaluate TTPXHunter on the augmented sentenc
92.42
%
f1-score on the augmented dataset, and it also outperforms existing state-of-the-art TTP extraction method by achieving an
97.09
%
when evaluated over the report dataset. TTPXHunter significantly improves cybersecurity threat intelligence by offering qu

The field of Natural Language Processing (NLP) is currently undergoing a revolutionary transformation driven by the powe
incident detection has significantly increased. IoT devices are expanding rapidly, resulting in a growing need for efficient te
architecture that leverages the Bidirectional Encoder Representations from Transformers (BERT) model for cyber threat de
effectively represented network traffic data in a structured format by combining PPFLE with the Byte-level Byte-Pair Enco
(CNNs) or Recurrent Neural Networks (RNNs), in cyber threat detection. Employing the Edge-IIoTset cybersecurity datase
solutions such as GAN-Transformer-based architectures and CNN-LSTM models. With an inference time of less than 0.15
devices.

Industry 4.0 is fundamentally based on networked systems. Real-time communication between machines, sensors, devices,
connectedness in conjunction with information transparency. Industry 4.0-based wireless sensor networks (WSNs) are an in
and optimize processes. Increased connections make people more susceptible to cyberattacks, necessitating the use of stron
proposed framework enhances the cybersecurity of WSNs in Industry 4.0 using a multi-criteria approach. It implements ma
nature of the attacks. We implemented three models, i.e., Decision Tree, MLP, and Autoencoder, as proposed algorithms in
cybersecurity intrusions in WSNs of Industry 4.0, we implemented Autoencoder model. Simulation results show that the D
provides an accuracy of 99.52%, precision of 99.5%, recall of 99.5%, and F1 score of 99.5% in the detection and classifica
The rapid evolution of modern automobiles into intelligent and interconnected entities presents new challenges in cybersecu
(DL) approaches employed in developing sophisticated IDS for safeguarding IVNs against potential cyber-attacks. Specific
taxonomy categorizing IDS techniques into conventional ML, DL, and hybrid models, highlighting their applicability in de
detection methods, emphasizing the significant advantages of AI-driven approaches in identifying novel and sophisticated i
applications within IVNs. Additionally, we explore emerging technologies, such as Federated Learning (FL) and Transfer L
research, focusing on integrating real-time data analysis, cross-layer security measures, and collaborative IDS frameworks.

Ensuring data privacy and protection has become paramount in the era of deep learning. Unlearnable examples are propose
predominantly impact low-level features, making them vulnerable to common countermeasures. In contrast, semantic imag
Deep Hiding (DH) scheme that adaptively hides semantic images enriched with high-level features. We employ an Invertib
Concentration module, designed to work with the INN, regularizing the intra-class variance of these perturbations. To furth
generates similar semantic images for samples within the same classes, thereby enlarging the inter-class distance and narrow
robustness for unlearnable examples, demonstrating its efficacy in preventing unauthorized data exploitation.

Demand response (DR) is a crucial component of power systems that can offer operating reserves by utilizing flexible load
performance of DR, it also introduces cyber-security threats, i.e., deception cyber-attacks (DCAs), which can lead to DR ou
is developed based on a distributed control framework for offering operating reserve to power systems. In addition, conside
response, power fluctuation, etc. Furthermore, an anti-attack secure distributed control is developed for DR to counteract ag
by power systems, despite arbitrary DCAs. Finally, case studies validate the efficacy of the proposed control method.

We investigate load redistribution (LR) attacks on integrated electricity-gas systems (IEGSs) and proposes a bilevel mixed-
modified reformulation and decomposition (R&D) algorithm is developed to solve this model in a master-subproblem fram
and solution optimality.

As smart grids (SGs) increasingly rely on advanced technologies like sensors and communication systems for efficient ener
resilience of modern energy systems. While extensive research has been conducted, a comprehensive exploration of proacti
survey begins with an overview of related works and our distinct contributions, followed by an examination of SG infrastru
taxonomy of DL approaches, highlighting their roles and relevance in the proactive security of SG. Subsequently, we analy
overview of benchmark data sets used in this domain to substantiate the discourse. This is followed by a critical discussion
outlook on future developments in this key field.

This article is concerned with the secure distributed economic dispatch (DED) problem of microgrids. A quantized distribu
generators (DGs) in order to meet the total load demand at the lowest generation cost under the DG capacity limits while en
the effects of quantization errors can be eliminated. Next, utilizing matrix norm analysis and mathematical induction, a suff
using sign transmissions). Moreover, an encryption–decryption scheme is developed based on quantized outputs, which ens
are confirmed through a simulated

This paper describes a simulation-based approach for automated risk assessment of complex cyber-physical systems to supp
other threats. In this way, the approach deals with inter-dependencies within the target system, automatically finding attack
of system assets and their possible relationships, along with the associated threats, causes and effects in a generic context. A
which threats are relevant and create a cause-and-effect simulation of those threats. This allows threat likelihoods and risk l
by modelling a published case study of an attack on a steel mill. Given reasonable assumptions about security controls in pl
performance.

Privacy-preserving data evaluation is one of the prominent research topics in the Big Data era. In many data evaluation app
requirement. Aiming at solving this problem, numerous fuzzy encryption systems for different similarity metrics have been
encryption scheme for privacy-preserving data evaluation based on overlap distance, which can work in an integer domain
during decryption stage negative correlation with the size of the threshold, which is pretty practical for some applications e
applied to some scenarios, such as fuzzy keyword searchable encryption and attribute-hiding closest substring encryption.

In recent years, issues of privacy preservation in data mining and machine learning have received more and more attention
machine learning models without privacy concerns. In this paper, we address the distressing problem of privacy-preservatio
part is privately kept by a data user, the second one is securely stored by the miner, and the rest is publicly known by both t
achieves a high level of privacy but also guarantees the accuracy of the classification model. The experimental results show
model.
With the wider adoption of machine learning and increasing concern about data privacy, federated learning (FL) has receiv
the coordination of a central server to construct a global FL model. Improvements upon standard FL include (i) reducing th
protocols. However, state-of-the-art PPAgg protocols do not interoperate easily with gradient sparsification due to the heter
on the nature of the PPAgg protocol and gradient sparsification technique, providing both security guarantees and commun
proposed protocol makes it attractive for both implementation and further improvements.

Future energy systems (FESs) require greater interaction, integration, and cooperation between physical infrastructure, cybe
effectiveness, sustainability, security and safety of energy generation and use. In this paper, we will first present an overvie

We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen

Future carbon-neutral power systems impose many challenges; one is the urgent need for a simulation platform that allows
response considering primary frequency control and emergency frequency control: under-frequency load-shedding (UFLS)
simulator for test system modelling and the remainder used to implement the UFLS protection scheme. Two connections of
cybernetic layer of the testbed models a test system, controls the real-time simulation, and implements digital communicati
show the appropriate performance of the proposed testbed.

The smart grid is becoming one of the fundamental cyber-physical systems due to the employment of information and com
smart grid can procure electricity from various supply sources, and then sell it to the customers. Therefore, it is critical for r
pricing DSM. We model and analyze the interactions between the retailer and electricity customers as a four-stage Stackelb
the optimal retail price to offer to the customers, to maximize its profit. In the fourth stage, the customers, who are the follo
higher utility using our proposed decision-making scheme. We also analyze how the system parameters affect the procurem

Cooperative communications is a core research area in wireless vehicular networks (WVNs), thanks to its capability to prov
scheme in order to select the optimal relay from a set of available relays for data transmission. However, due to the mobilit
robust relay selection scheme (RSS) that guarantees a satisfactory overall achievable performance in the presence of an out
scenario with relay selection as a Markov decision process (MDP) and proposes two deep Q-networks (DQNs), namely DQ
relay from a set of multiple relays. We then compare the proposed RSS with the conventional methods and evaluate the per
probability by approximately 15% and 30%, respectively, compared to the standard ARMA approach.

Federated learning (FL) allows clients at the edge to learn a shared global model without disclosing their private data. How
developed to combat poisoning attacks, they all fall short of securing practical FL scenarios with heterogeneous and unbala
to the fundamental principle of privacy protection in FL. It is still challenging to devise an effective defense approach that a
FL when the training data is not independent and identically distributed (non-IID). We then present HeteroFL, a novel FL s
we devise an adaptive attack specifically for HeteroFL, aimed at offering a more thorough evaluation of its robustness. Our
model accuracies comparable to the baseline, whereas other defenses suffer a significant accuracy reduction ranging

We study automated intrusion response and formulate the interaction between an attacker and a defender as an optimal stop
dynamic attacker, i.e. an attacker that adapts its strategy in response to the defender strategy. Further, the optimal stopping
algorithm that learns Nash equilibria through stochastic approximation. We show that T-FP outperforms a state-of-the-art a
statistics are collected that drive simulation runs and where learned strategies are evaluated. We argue that this approach ca

Safe and secure operations of robotic systems are of paramount importance. Aiming for achieving the trusted operations of
algorithm is specifically designed to reduce the cyber vulnerability of the Robot Operating System (ROS), a well-known m
cyberattacks) on the GVR-BOT ground vehicle, a replicate of a military ground robot, developed by the United States Arm
computer. We collect experimental data and train our CNN based on two different operating conditions, namely, legitimate
and overlapping sliding epochs to efficiently feed the network traffic data to our CNN system. Our research indicates the ef
minimum detection times. In addition, we also compare and demonstrate the relative merits of our proposed algorithm with
We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen

We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen

We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen

We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen

We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen

We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen

We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen

We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen

We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen

We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen

We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen

We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen
We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen

We address the problem of indexing encrypted data outsourced to an external cloud server to support server-side execution
guarantee protection against static inferences. Our indexing approach does not require any modifications to the server-side
(PostgreSQL) and a key-value database (Redis). We carried out extensive experiments evaluating client-storage requiremen

In recent years, issues of privacy preservation in data mining and machine learning have received more and more attention
machine learning models without privacy concerns. In this paper, we address the distressing problem of privacy-preservatio
part is privately kept by a data user, the second one is securely stored by the miner, and the rest is publicly known by both t
achieves a high level of privacy but also guarantees the accuracy of the classification model. The experimental results show
model.

With the wider adoption of machine learning and increasing concern about data privacy, federated learning (FL) has receiv
the coordination of a central server to construct a global FL model. Improvements upon standard FL include (i) reducing th
protocols. However, state-of-the-art PPAgg protocols do not interoperate easily with gradient sparsification due to the heter
on the nature of the PPAgg protocol and gradient sparsification technique, providing both security guarantees and commun
proposed protocol makes it attractive for both implementation and further improvements

Future energy systems (FESs) require greater interaction, integration, and cooperation between physical infrastructure, cybe
effectiveness, sustainability, security and safety of energy generation and use. In this paper, we will first present an overvie

Cyber–physical–social system (CPSS) is a novel emerging paradigm that offers innovative services through the in-depth bu
intelligent human–machine interaction in cyber-space. A smart city is defined as a connectable, sensible, accessible, ubiqui
networks interconnect with wireless mobile devices such as smart phones with an Internet-based backbone with cloud servi
and flows it from the human physical systems such as the condition of traffic, bridges, parking space, roads or buildings, qu
requirements for security, privacy, safety, mobility, and the processing of huge amounts of information called big data. In a
Transportation and energy networks are important arteries for the urban environment, and citywide systems should be funct
is surging to recognize the importance and involvement of CPSS in social dimensions that have the power

Cyber–physical–social system (CPSS) is a novel emerging paradigm that offers innovative services through the in-depth bu
intelligent human–machine interaction in cyber-space. A smart city is defined as a connectable, sensible, accessible, ubiqui
networks interconnect with wireless mobile devices such as smart phones with an Internet-based backbone with cloud servi
and flows it from the human physical systems such as the condition of traffic, bridges, parking space, roads or buildings, qu
requirements for security, privacy, safety, mobility, and the processing of huge amounts of information called big data. In a
Transportation and energy networks are important arteries for the urban environment, and citywide systems should be funct
is surging to recognize the importance and involvement of CPSS in social dimensions that have the power

The smart grid is becoming one of the fundamental cyber-physical systems due to the employment of information and com
smart grid can procure electricity from various supply sources, and then sell it to the customers. Therefore, it is critical for r
pricing DSM. We model and analyze the interactions between the retailer and electricity customers as a four-stage Stackelb
the optimal retail price to offer to the customers, to maximize its profit. In the fourth stage, the customers, who are the follo
higher utility using our proposed decision-making scheme. We also analyze how the system parameters affect the procurem

Cooperative communications is a core research area in wireless vehicular networks (WVNs), thanks to its capability to prov
scheme in order to select the optimal relay from a set of available relays for data transmission. However, due to the mobilit
robust relay selection scheme (RSS) that guarantees a satisfactory overall achievable performance in the presence of an out
scenario with relay selection as a Markov decision process (MDP) and proposes two deep Q-networks (DQNs), namely DQ
relay from a set of multiple relays. We then compare the proposed RSS with the conventional methods and evaluate the per
probability by approximately 15% and 30%, respectively, compared to the standard ARMA approach.
Federated learning (FL) allows clients at the edge to learn a shared global model without disclosing their private data. How
developed to combat poisoning attacks, they all fall short of securing practical FL scenarios with heterogeneous and unbala
to the fundamental principle of privacy protection in FL. It is still challenging to devise an effective defense approach that a
FL when the training data is not independent and identically distributed (non-IID). We then present HeteroFL, a novel FL s
we devise an adaptive attack specifically for HeteroFL, aimed at offering a more thorough evaluation of its robustness. Our
model accuracies comparable to the baseline, whereas other defenses suffer a significant accuracy reduction ranging

We study automated intrusion response and formulate the interaction between an attacker and a defender as an optimal stop
dynamic attacker, i.e. an attacker that adapts its strategy in response to the defender strategy. Further, the optimal stopping
algorithm that learns Nash equilibria through stochastic approximation. We show that T-FP outperforms a state-of-the-art a
statistics are collected that drive simulation runs and where learned strategies are evaluated. We argue that this approach ca

Safe and secure operations of robotic systems are of paramount importance. Aiming for achieving the trusted operations of
algorithm is specifically designed to reduce the cyber vulnerability of the Robot Operating System (ROS), a well-known m
cyberattacks) on the GVR-BOT ground vehicle, a replicate of a military ground robot, developed by the United States Arm
computer. We collect experimental data and train our CNN based on two different operating conditions, namely, legitimate
and overlapping sliding epochs to efficiently feed the network traffic data to our CNN system. Our research indicates the ef
minimum detection times. In addition, we also compare and demonstrate the relative merits of our proposed algorithm with

Control over networks is envisioned to be one of the driving applications of future mobile networks. Networked control sys
wireless star network. A centralized scheduler located at the central node, i.e., base station (BS), determines the transmissio
probability. Moreover, each controller estimates the system state remotely based on available information. In such a setting
the minimum normalized mean squared error (nMSE) in a given finite horizon (FH). We compare the performance of our p
when compared to the best performing scheduling policy among the selected policies from the state-of-the-art. Moreover, th

With the rise of smart working and recent global events, the risk of cyberattacks is increasing steadily. Sometimes adversar
automated methods. This work proposes the DARD (Deceptive Approaches for Robust Defense against IP theft) system, a
new deceptive repository that misleads popular automatic approaches, resulting in clusters of documents that are significan
techniques. The paper presents four deceptive operations (Basic Shuffle, Shuffle increment, Shuffle reduction, and Change
knowledge and expertise. Through extensive experiments, we show that the DARD system can deceive both automatic topi
Intellectual Property (IP) theft

This paper introduces the Least Increase aversion (LIA) protocol to investigate the relative impact of factors that may trigge
target experience may cause undesired discomfort. In the first session, the participant briefly encounter all factors at the ma
factors. This approach ranks the factors from mildest to worst and helps detect individual susceptibility to cybersickness tri
only confirm the protocol's capability to accurately discern individual rankings of various factors to cybersickness but also

Over the past few years, the concept of Virtual Reality (VR) has attracted increasing interest thanks to its extensive industri
multi-party interactions will likely require the scene to be processed by an external server and then streamed to the visors. H
application is crucial. To this end, we collected more than 4 hours of traces in a real setup and analyzed their temporal corre
frame size, which can be instrumental in the design of dynamic resource allocation algorithms. Our results show that even t
scenario, providing the required QoS while minimizing resource usage

The growing adoption of the Internet of Things (IoT) has brought a significant increase in attacks targeting those devices. M
IoT scenarios. Static datasets get outdated due to evolving IoT architectures and threat landscape; meanwhile, the testbeds u
attackers. Gotham is used to build an IoT scenario composed of 100 emulated devices communicating via MQTT, CoAP an
teaming tools performing DoS, scanning, and attacks targeting IoT protocols. The testbed has many purposes, including a c
the-art attacks and topologies to share scenarios and datasets that reflect the current IoT settings and threat landscape

Choosing the right features (feature selection) is important in machine learning, especially for complex data (high-dimensio
methods (ACO, PSO, BA, DE, SA) and a new method called MEL. MEL uses a multi-tasking approach to learn from multi
outperforms the traditional methods on most datasets. This suggests MEL is better suited for complex data and finding key
Air pollution is a severe environmental problem in urban areas. Accurate air quality prediction can help governments and in
As a classic time series forecasting model, the AutoRegressive Integrated Moving Average (ARIMA) has been widely adop
and the lack of additional context information, i.e., the spatial relationships among monitor stations, traditional ARIMA mo
can achieve higher accuracy, a mass of training data, heavy computing, and time cost are required. In this paper, we propos
multiple monitoring stations. The proposed model consists of three components: (1) an extended ARIMA to predict matrix
(2) the Empirical Mode Decomposition (EMD) to decompose the air quality time series data into multiple smooth sub-serie
denoise the expanded matrix. Experimental results on the public dataset show that our proposed model outperforms the stat

The e-commerce industry’s rapid growth, accelerated by the COVID-19 pandemic, has led to an alarming increase in digita
to keep pace due to limited real-world datasets. Advances in artificial intelligence, Machine Learning and cloud computing
platforms like eBay and Facebook are lacking depth. Existing reviews provide broad overviews but fail to grasp the intricac
that the accuracy algorithms. In this process, E-Commerce Fraud Detection was taken from dataset repository.

"This study explores ship object detection using Convolutional Neural Networks (CNN), YOLOv5, and YOLOv8, evaluatin
execution times due to their complex architecture. YOLOv5, an advanced real-time object detection model, balances accura
these capabilities, enhancing accuracy and reducing error rates through improved network structures and optimization techn

"

Accurate forecasting of energy consumption is essential for efficient resource allocation, grid management, and sustainable
prediction. The Stacked LSTM architecture enables capturing complex temporal dependencies in energy consumption data,
initializations and snapshots of the training process. By ensembling predictions from these diverse models, improved accur
models and state-of-the-art techniques. The results demonstrate that the Stacked LSTM Snapshot Ensemble method outperf
the impact of different hyperparameters and model configurations on predictive performance.

A problem with machine learning (ML) techniques for detecting intrusions in the Internet of Things (IoT) is that they are in
strategies of cost sensitive learning and multitask learning into a hybrid ML model to address these two challenges. The hyb
hinge loss layer is enhanced to make a classifier strong against low-distributed intrusions. Moreover, to detect unknown att
averagely 92.2%, 96.2%, and 94.3%, respectively, over other approaches.

A pretrained quantum inspired deep neural network is proposed in this work, whichis constructed based on quantum theory
superposition statesfor words to embed more textual features. Then, a QPFE-ERNIEmodel isdesigned by merging the sema
schematic quantumcircuit diagrams are provided, which has potential impetus forthe future realization of quantum NLP wit
Finally, the experiment results demonstrate QPFE-ERNIE is significantly better for sentiment classification than gated recu

Grid-based recommendation algorithms traditionally view users and items as abstract nodes, relying on selection relationsh
the standard substance diffusion algorithm by incorporating the influence of user ratings on recommended items, introducin
accuracy by taking into account the user's rating behavior, thereby refining the diffusion process. A moderating factor is int
resource allocation vector and resource transfer matrix ensures a more efficient and effective distribution of recommendatio
recommendation quality compared to traditional metrics.Experiments conducted on the MovieLens training dataset demons
superior performance in terms of recommendation accuracy and hit rate, validating the effectiveness of the proposed enhan

Machine learning techniques have garnered interest insecurity applications due to their rapid processing capabilities
and real-time predictions. However, imbalanced data distributionis a prevalent issue in IIoT environments, adversely affect
specifically targeting IIoT systems. The proposed model enhancesdiversityin the minority classes by generating unique syn
ofprecision, recall & F-Score while mitigating over-generalizationby evenly distributing newly generated samples within m
proposedmodel efficiently detects attacks with high performance comparedto state-of-the-art techniques. Our research cont
the security of IIoT systems while handling class imbalanceissues.

Faults in electrical machines are mostly detected by analyzing direct measurements. However, an early detection can be dif
to classify the machine's quality at the End of Line (EoL) test bench and for condition monitoring is studied. With a transie
on the simulation data and evaluated for an EoL test procedure as well as eccentricity classification where a large portion o
the measurement analysis. If no fault cases are available for training, an autoencoder can be utilized to identify the fault cas
remains.
A problem with machine learning (ML) techniques for detecting intrusions in the Internet of Things (IoT) is that they are in
strategies of cost-sensitive learning and multitask learning into a hybrid ML model to address these two challenges. The hy
hinge loss layer is enhanced to make a classifier strong against low-distributed intrusions. Moreover, to detect unknown att
averagely 92.2%, 96.2%, and 94.3%, respectively, over other approaches.

Several recent research papers in the Internet of Medical Things (IoMT) domain employ machine learning techniques to de
to revolutionize healthcare, several challenges remain.The conventional machine learning models in the IoMT domain are s
machine learning models paradigm, the models must be re-trained again, even to incorporate a few sets of additional sampl
propose an edge-based incremental learning framework with a novel feature selection algorithm for intelligent diagnosis of
reducing privacy and security issues. Addressing the issue of excessive features, which might increase the computational bu
Solution). We propose two incremental algorithms inspired by Aggregated Mondrian Forests and Half-Space Trees for clas
the proposed model for anomaly detection gives an accuracy of 97.22%, which is better by 1.76% than the best-performing

In many scientific endeavors, increasingly abstract representations of data allow for new interpretive methodologies and co
relevant areas. Thus, the development of new and improved methods for segmentation remains an active area of research. W
associations between pixels and corresponding/referent objects and gathering those objects afterward. Topological analysis
classify. This approach is empirically motivated since phenomena of interest often appear as subsets of topological priors in
segmentation target. In this article, we describe an approach to creating learnable topological elements, explore the applicat
and requiring marginal training data.

Because of community quarantines and lockdowns during COVID–19 times, the Philippine’s Department of Education (De
amidst the pandemic. Learners’ LM are classified through the use of an Algorithm for Learning Delivery Modality as recom
year. In this study, we introduced an approach to classifying learner’s LM using machine learning (ML) techniques. We com
Naïve Bayes (NB). Learner’s enrolment and survey form (LESF) data from the repository of a local private high school in t
integrated into the five ML classifiers as data feature reduction techniques. Results show that the combination of MLP NN
feature, modified asynchronously, is highly characterized by low educational attainment and unstable employment status of

Grid-based recommendation algorithms view users and items as abstract nodes, and the information utilised by the algorith
recommendation algorithm. The aim of this paper is to propose improvements on the standard substance diffusion algorithm
the recommendation algorithm. An average ranking score evaluation index is introduced to quantify user satisfaction with t
filtering systems and network structure based recommendation systems in terms of recommendation accuracy and hit rate.

Many social media users express concerns about vaccines and their side effects on Twitter. These concerns lead to a compr
are geotagged, clustering them according to their sentiments could help identify locations that may likely experience vaccin
classified into three sentiment classes—positive, negative, and neutral. The quality of the classification outputs was achieve
accuracy of 71% with an average area under the curve of 85%. The point-based location technique was used to calculate the
of this research shows that discussions on social media can be analyzed to identify hotspots during a disease outbreak, whic

This article aims to study the performance of machine learning models in forecasting gender based on the students' open ed
perceptions of knowledge, skills, and attitudes or values related to open education and its subcompetencies from a 30-item
between machine learning models, and 4) an analysis from explainable machine learning models to find relevant features to
attitudes or values related to open education competency.

Detection and prevention of fraudulent transactions in e-commerce platforms have always been the focus of transaction sec
frauds, which have not considered the dynamic behaviors of users from multiple perspectives. This leads to an inefficient d
First, we establish a process model concerning the business-to-customer (B2C) e-commerce platform, by incorporating the
machine (SVM)-based classification model that can detect fraud behaviors. We demonstrate the effectiveness of our metho
In the past few years, numerous methods of attack against recommendation systems have been developed. Cellphones, sma
higher exchange of data, the challenges in this domain lead to increased security issues. Therefore, intrusion detection syste
accuracy of machine learning and deep learning approaches for research in security for IoT consumer devices has gained tr
parameters to a cloud server, which helps in ensuring the security of data. However, communication channels can still be at
been proposed that detects the attacks on the SDN network incoming from the IoT consumer devices and recommends that
training has been implemented. Simulation shows that the proposed approach’s well-designed recommender system has out
already existing techniques

Emotion recognition based on electroencephalography (EEG) has received much attention in recent years, and there is more
deep learning model is proposed for EEG emotion recognition. The proposed approach extracts the critical feature informat
encoder is used to encode the EEG signal and extract the spatial features, and the band attention mechanism is introduced to
information. The performance of the proposed model is analyzed on benchmark emotion databases such as DEAP and SEE
proposed model can effectively recognize emotions and has a good classification performance.

Deep semi-supervised learning (SSL) methods aim to utilize abundant unlabeled data to improve the seen-class classificatio
problem as safe deep semi-supervised learning with unseen-class unlabeled data. One intuitive solution is removing these u
model, and the small number of labeled data. To this end, we propose a safe SSL method called SAFE R -STUDENT from
based on unseen-class data mined by teacher model from unlabeled data, we calibrate student model by newly proposed U
(WCBE) loss to boost seen-class classification of student model. Extensive studies show that SAFE R -STUDENT remarka

With the increasing prevalence of encrypted network traffic, cybersecurity analysts have been turning to machine learning (
adapt in this dynamic environment, ML models must additionally provide contextualized uncertainty quantification to their
label assignment and when the traffic is not likely to belong to any pretrained classes. We present a new public dataset of n
framework that is designed to rapidly train with modest data requirements and provide both calibrated predictive probabilit
demonstrate that our framework achieves an F1-score of 0.98 on our dataset and that it can extend to an enterprise network
flags uncertain traffic and, upon retraining, accurately incorporates the new data

Knowledge tracing is a well-known problem in AI for education, consisting of monitoring how the knowledge state of stud
deep learning techniques. Despite their satisfactory performances, they have some pitfalls, e.g., modeling one skill at a time
also been explored. With this systematic literature review, we aim to illustrate the state of the art in this field. Specifically,
qualitative analysis to distill a taxonomy with the following three dimensions: knowledge source, knowledge representation

Cross-subject electroencephalogram (EEG) based seizure subtype classification is very important in precise epilepsy diagno
available in clinical practice. This paper proposes Multi-Branch Mutual-Distillation (MBMD) Transformer for cross-subjec
Transformer by our designed multi-branch encoder blocks. A mutual-distillation strategy is proposed to transfer knowledge
traditional machine learning and state-of-the-art deep learning approaches. To our knowledge, this is the first work on know

Sit-to-stand transition phase identification is vital in the control of a wearable exoskeleton robot for assisting patients to sta
namely, the initial sitting phase, the flexion momentum phase, the momentum transfer phase, the extension phase, and the s
we designed a novel CNN-BiLSTM-Attention algorithm to identify the three transition phases, namely, the flexion momen
acceleration and angular velocity data features for the sit-to-stand transition phase identification were validated for the mod
the proposed
CNN-BiLSTM-Attention algorithm achieved the highest
average classification accuracy of 99.5% for all five phases
when compared to both traditional machine learning algorithms and deep learning algorithms on our customized
dataset (STS-PD). The proposed sit-to-stand phase recognition algorithm could serve as a foundation for the
control of wearable exoskeletons and is important for the
further development of intelligent wearable exoskeleton
rehabilitation robots
The widespread success of deep learning in solving machine learning problems has fueled its adoption in many fields, from
produce erroneous output. It is very easy to generate such adversarial perturbations even for state-of-the-art models, yet imm
this work, we survey some of the most important contributions in the field of adversarial robustness. We pay particular atte

Electromyographic (EMG) signals have gained popularity for controlling prostheses and exoskeletons, particularly in the fi
Asian race features, are scarce. Additionally, deep learning algorithms are rarely used for human motion intention recogniti
volume, the JJ dataset, which includes approximately 13,350 clean EMG segments of 10 gait phases from 15 people. This i
Our research explores and compares multiple key issues in this area, including the comparison of sliding time window meth
calf muscles in amputees. Our experiments demonstrate that the adjusted ResNet can achieve significant classification accu
and effective method for lower limb human motion intention pattern recognition.

Major Depression Disorder (MDD) is a common yet destructive mental disorder that affects millions of people worldwide.
diagnosis. However, there are still some challenges in data quality and data size of EEG: (1) A large amount of noise is inev
model training. Both of the challenges cause the overfitting problem, especially for deep learning methods. In this paper, w
designing the Forward Diffusion Noisy Training Module. Then we increase the size and diversity of data to help the model
comprehensive experiments to test the overall performance
and each module’s effectiveness. The framework was validated on two public MDD diagnosis datasets, achieving the
state-of-the-art performance.

A recent trend in machine learning has been to enrich learned models with the ability to explain their own predictions. The
is not given and the goal is instead to discover the underlying structure of the data, for example, its clusters. While powerfu
can, for the first time, explain cluster assignments in terms of input features in an efficient and reliable manner. It is based o
input features. Several showcases demonstrate the ability of our method to assess the quality of learned clusters and to extra

This paper investigates various multi-agent reinforcement learning (MARL) techniques for designing grant-free random acc
limitations in terms of scalability and suitability for mMTC. To address scalability and practicality of the proposed methods
algorithms with parameter sharing (PS) and compare their policies with the deep recurrent Q-network (DRQN). Our simula
correlated traffic model, which is more descriptive of mMTC scenarios, and show that the proposed algorithm can easily ad

A Transfer Function approach was recently demonstrated to mitigate data mismatches at the acquisition level for a single u
(M2M) Transfer Function, which possesses the ability to mitigate data mismatches at a machine level, i.e., mismatches betw
multiple sources or scanners, or facilitating the transfer of DL models between machines with ease. We tested the proposed
using two different calibration phantoms. Without the proposed calibration method, the mean classification accuracy when
increased to approximately 90%, and the AUC rose to the 0.99. Additional observations include that shifts in statistics for t
implementation inspired by Wiener filtering provided an effective method for transferring the domain from one machine to
Otago Exercise Program (OEP) is a rehabilitation program for older adults to improve frailty, sarcopenia,
and balance. Accurate monitoring of patient involvement
in OEP is challenging, as self-reports (diaries) are often
unreliable. The development of wearable sensors and their
use in Human Activity Recognition (HAR) systems has lead
to a revolution in healthcare. However, the use of such
HAR systems for OEP still shows limited performance.
The objective of this study is to build an unobtrusive and
accurate system to monitor OEP for older adults. Data
was collected from 18 older adults wearing a single waistmounted Inertial Measurement Unit (IMU). Two datasets
were recorded, one in a laboratory setting, and one at the
homes of the patients. A hierarchical system is proposed
with two stages: 1) using a deep learning model to
recognize whether the patients are performing OEP or
activities of daily life (ADLs) using a 10-minute sliding
window; 2) based on stage 1, using a 6-second sliding
window to recognize the OEP sub-classes. Results showed that in stage 1, OEP could be recognized with window-wise
f1-scores over 0.95 and Intersection-over-Union (IoU) f1-
scores over 0.85 for both datasets. In stage 2, for the home
scenario, four activities could be recognized with f1-scores
over 0.8: ankle plantarflexors, abdominal muscles, knee
bends, and sit-to-stand. These results showed the potential
of monitoring the compliance of OEP using a single IMU in
daily life. Also, some OEP sub-classes are possible to be
recognized for further analysis

Computational biomechanical analysis plays a pivotal role in understanding and improving human movements and physica
latency. In recent years, data-driven methods have emerged as a promising alternative due to their fast execution speed, but
muscle forces without any label information during model training. In addition, the proposed method could also identify pe
behavior of the deep neural network. Experimental validations on the wrist joint from six healthy subjects are performed, an
and higher coefficient of determination compared with baseline methods, which have to use the labeled
surface electromyography (sEMG) signals, and it can also
identify muscle-tendon parameters accurately, demonstrating the effectiveness of the proposed physics-informed
deep learning method

Electrocardiography (ECG) is a non-invasive tool for predicting cardiovascular diseases (CVDs). Current ECG-based diagn
performance on unseen datasets greatly hinder the widespread application of deep learning-based models. Addressing them
supervision. In the ECGMatch, an ECGAugment module is developed for weak and strong ECG data augmentation, which
generation and refinement, which mitigates the label scarcity problem. Finally, a label correlation alignment module is prop
protocols demonstrate the effectiveness and stability of the proposed model, especially on unseen datasets. As such, this mo

Machine learning (ML) has been successfully applied to classification tasks in many domains, including computer vision, c
(AML) attacks. In one type of AML attack, the adversary trains a surrogate classifier (called the attacker’s classifier) to pro
their vulnerabilities to AML attacks. Specifically, we consider several exemplary protocol and modulation classifiers, desig
performance under three types of low-power AML perturbations (FGSM, PGD, and DeepFool), considering different amou
reveal that in this case, the AML attack significantly degrades the defender’s classification accuracy. We gradually reduce t
defender’s classifier and its power is relatively low, the attack is still significant. We also study various practical issues rela
Even under such imperfections, a low-power AML attack can still significantly reduce the defender’s classification accurac
art defense strategies. The proposed defense approach increases the classification accuracy by up to 50%, even in scenarios
Observational causal inference is useful for decision-making in medicine when randomized clinical trials (RCTs) are infeas
growth of deep learning for capturing rich representations of multimodal data offers a unique opportunity to develop and te
classes of antihypertensive on incident cancer risk. We develop a transformer-based model, targeted bidirectional EHR tran
multiple experiments on semi-synthetic derivations of our dataset with various types and intensities of confounding. In orde
(SAE) from ground truth] compared with benchmark estimations. Finally, our model provides an estimate of class-wise ant

Machine learning has achieved remarkable success across diverse domains. Nevertheless, concerns about interpretability in
known for their higher interpretability, are preferred in these domains. Similar to DNNs, classical ML classifiers can exhibi
misclassified tests so that such tests can be identified earlier with limited manual labeling costs. However, when applying to
methods cannot be adapted to classical ML models due to mismatched model mutation rules; 3) Confidence-based methods
MLPrior, a test prioritization approach specifically tailored for classical ML models. MLPrior leverages the characteristics
more likely to be misclassified, and 2) tests closer to the model's decision boundary are more likely to be misclassified. Bui
notion, MLPrior generates attribute features of each test based on its attribute values, which can indirectly reveal the proxim
predict the misclassification probability of each test based on its final vector and ranks tests accordingly. We conducted an
compared test prioritization approaches, with an average improvement of 14.74% $\sim$ 66.93% on natural datasets, 18.55

The Internet of Things (IoT) has revolutionized our lives by generating large amounts of data, however, the data needs to b
experience. Different methods are introduced for NTC, but recently Machine Learning solutions have received high attentio
shows promise but is computationally intensive for resource-constrained IoT devices. Knowledge distillation is a solution t
experiments, we show that the student model achieves a balance between accuracy and efficiency. It exhibits similar accura
knowledge distillation technique effectively transfers knowledge from the teacher model to the student model, even with re
off between model capacity and computational cost, suggesting that increasing model size beyond a certain point may not b

Customers use reviews as a primary source of information to judge a product or service. Positive reviews help boost compa
case due to competitive advantage. Organizations can use fake (i.e., misleading or fraudulent) reviews to generate fast profi
methods fall short of achieving highly accurate detection results for unbalanced classes. We aimed to create a spam review
efficient fake reviews detection. We used n -gram models to effectively model language data for feature retrieval. The expe
conventional machine learning techniques [Naïve Bayes, logistic regression, K-nearest neighbor (KNN), random forest, ext

Industry 5.0 is a emerging transformative model that aims to develop a hyperconnected, automated, and data-driven industr
Intrusion Detection Systems (IDS) have the potential to recognize intrusions with high accuracy. However, these models ar
explainable and resilient IDS for Industry 5.0. The proposed IDS is designed by combining bidirectional long short-term m
SHapley Additive exPlanations (SHAP) mechanism to interpret and understand the features that contributed the most in the
the CICDDoS2019 dataset confirms the superiority of the proposed IDS over some recent approaches.

Consumer Electronics (CEs) are smart devices using IoT for connectivity. They’re susceptible to attacks like DoS, DDoS, a
causing vehicle failures. Existing ML/DL based IDS have high classification accuracy and robustness in traditional internet
these intrusion detection algorithms with other algorithms are not sufficiently comprehensive to evaluate their performance
hybrid feature selection model based on chi-square test and information gain combined Ig-Chi, which effectively reduces th
on the data after feature selection. The experiments on four public data sets demonstrate that this method surpasses six ML/

Micro-expression recognition based on ima- ges has made some progress, yet limitations persist. For instance, image-based
technology can record brain activity associated with micro-expressions and identify them objectively from a neurophysiolo
real-time Supervision and Emotional Expression Suppression (SEES) experimental paradigm to collect video and EEG data
efficiencies at both macro- and micro-levels. The participants exhibited lower connection density, global efficiency, and no
forest algorithm and applied them to various classifiers, including Support Vector Machine (SVM), Gradient-Boosted Deci
with SVM exhibiting the highest accuracy of 92.6% when 15 channels were selected. This study provides a new neuroscien
Traffic management and sustainable mobility are the central topics for intelligent transportation systems (ITS). By means o
information are high. It requires either direct measures in the network road by installing large number of sensors (more prec
solution granting traffic flow data in each road segment of the whole network by reconstructing the computation by means
learning for improving the state-of-the-art solutions of PDE. The result has been a higher precision with respect to PDE-bas
architecture proposed. The research result has been obtained in the framework of both the Sii-Mobility national project on t

Condition-based maintenance is a decision-making strategy using condition monitoring information to optimize the availab
reliability of the system through maintenance policies and, consequently, reducing costs arising from the failure. These data
regression algorithms were compared for RUL prediction, namely: Support Vector Regression (SVR), Decision Tree (DT),
pre-processing the input data used on the predictive modeling. We optimize the models hyperparameters using grid-search
the most promising to perform the prognostic task in small datasets, adapting itself to the distinct characteristics of the diffe
analyzed here.

Text sentiment analysis is an important task in natural language processing and has always been a hot research topic. Howe
computational resources, flexible word order, and high inflectional nature of the language. With the development of quantu
promote the development of quantum machine learning in low-resource language domains, we propose a quantum–classica
combines the proposed batch upload quantum recurrent neural network (BUQRNN) and parameter nonshared batch upload
achieves a maximum accuracy improvement of 0.993% in Bengali text classification tasks while reducing average model co

Leveraging patient data through machine learning techniques in disease care offers a multitude of substantial benefits. None
longitudinal laboratory data are renowned for their irregularity, temporality, absenteeism, and sparsity; In contrast, recruitm
progress (GLP) model that captures the overall progression of six common laboratory markers in prevalent cardiovascular c
the information embedded within interpolated data and amplify the performance of SSL. After GLP pretraining, it is transfe
After GLP processing, the classification exhibited a notable enhancement, with averaged accuracy rising from 0.63 to 0.90.
patient progression of cardiovascular laboratory parameters from one patient group to another, transcending the limitations
parameters. The potential for expanding this approach to encompass other diseases holds great promise. Clinical impact: Ou
cardiovascular event assessment.

The upsurge of Internet of Things (IoT) devices has increased their vulnerability to Distributed Denial of Service (DDoS) a
challenges highlight the importance of reliable detection and prevention measures. This paper introduces a novel Deep Ense
learning by integrating a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) network with a n
unit pruning to refine ensemble models, optimizing them for deployment on edge devices while maintaining a balance betw
both attack types. Furthermore, the testbed evaluation of the DEEPShield system under various load scenarios and network
17, and ISCX-12, the DEEPShield system consistently achieves an accuracy over 90% for both DDoS attack types. Further

Electroencephalogram (EEG) is widely used in basic and clinical neuroscience to explore neural states in various populatio
feature extraction methods for EEG classification remain elusive. Our study addressed the problem of EEG classification un
age predictions than using raw or canonically frequency-filtered EEG. Specifically, we employed multivariate intrinsic mod
of routine clinical EEG scans (n = 6540) from patients aged 1 to 103 years, we found that an ad-hoc CNN model without fi
oscillations). Our approach achieved a mean absolute error (MAE) of 13.76 ± 0.33 and a correlation coefficient of 0.64 ± 0
classification, wherein the adaptive signal decompositions such as the MIF can enhance CNN models’ performance in this

COVID-19 has become the most significant pandemic in recent years. Today, Mexico has recorded millions of infections a
algorithms provide good results, it is necessary to understand why a model makes specific predictions with a particular data
denoting between deaths and survivors. As a case of study, the positive cases detected during the winter season of 2020-202
Preliminary results suggest that age is essential when using a Random Forest model. Preliminary results suggest that age is
Contribution: This study incorporates competition-based learning (CBL) into machine learning courses. By engaging stude
technology, and showcase competitions can enhance their competition ability. Background: The CBL model seamlessly int
enhance their learning and translate knowledge into practical experience. Research Questions: The objective is to examine t
competitions and showcase competitions, and discusses the potential moderating effect of competition type on the relations
and information technology pretests and posttests in the 2nd and 17th weeks, respectively. In the 18th week, the students pr
enhance their information technology, while those participating in showcase competitions can improve their competitive ab
incorporating CBL into machine learning courses effectively cultivates students’ AI practical and competitive abilities.

Large-scale infectious diseases pose a tremendous risk to humans, with global outbreaks of COVID-19 causing millions of
assistance for prevention. In this paper, we propose an XGBoost-LSTM mixed framework that predicts the spread of infect
according to population flow can significantly improve prediction accuracy. Meanwhile, an XGBoost is used to predict the
combines transmission trends and fluctuations to predict infections accurately. The proposed method is evaluated on a data
practical value for large-scale infectious disease prediction.

Natural events have had a significant impact on overall flight activity, and the aviation industry plays a vital role in helping
plans during this time period will pay close attention to the development of tropical storms. This paper proposes a deep mu
multimodal fusion module is formed by deep fusion of the feature output by multiple submodal fusion modules, and the mu
enabling better decision-making with a proactive versus reactive posture. When multiple modalities coexist, features can be
effectively reduce the number of unnecessary flight cancellations compared to existing flight scheduling and assist the new

Traffic engineering (TE) is one of the most critical issues in networking, as it enables efficient and reliable network operati
prediction to enhance the performance of traditional approaches. However, current methods suffer from two major issues. F
network disturbance when numerous traffic flows need to be rerouted to adapt to traffic changes. Secondly, although traffic
propose a traffic prediction-based routing algorithm in which the routing rules can be applied to multiple time-steps withou
method that incorporates future traffic prediction. To address the high monitoring overhead, we present an approach that co
our proposal can achieve more than 80% of the optimal performance in reducing maximum link utilization while significan

Sea surface temperature (SST) is one of the most important parameters in the global ocean–atmosphere system, and its long
significance for fishery farming, marine ecological protection, and planning of maritime activities. Since the effective and p
SST. Inspired by the successful application of the transformer and its variants in natural language processing similar to time
Part) is developed by embedding the temporal information in the classic transformer, combining attention distillation and p
predictions with day granularity are achieved under univariate and multivariate patterns. With root mean square error and m
and six prediction horizons (i.e., 30, 60, 90, 180, 270, and 360 days). Experimental results demonstrate that the performanc

The poor generalization performance and heavy training burden of the gesture classification model contribute as two main b
developed on the basis of convolutional neural networks (CNNs) were explored and compared on a dataset consisting of 10
addition, the proposed model outperforms 4 common traditional classifiers (KNN, LDA, SVM, and Random Forest) using t
an accuracy of 87.94% achieved using calibration gestures that are different with model training, and an accuracy of 84.26%
complicated acquisition paradigm in the calibration process before using sEMG-based HMI systems.

Wearable sensors can be exploited for the indirect estimation of physiological parameters, such as breathing rate (BR). Inde
punctual (or brief, anyway) measurements. This article aims to perform an uncertainty analysis of BR indirect estimation m
estimation methods were employed, considering respiratory sinus arrhythmia (RSA), signal amplitude modulation (AM), an
algorithms (software) contributions in the measurement chain. The results show that both the considered sensors are quite a
obtained for the cardiac belt (a reduced 95% confidence interval is reported, with a maximum reduction of 4 bpm dependin
evidenced that the ML-based method is the most robust with respect to the sensors’ uncertainty (with no differences in the o
uncertainty) if RSA- and AM-based methods are considered.
Meta-learning empowers learning systems with the ability to acquire knowledge from multiple tasks, enabling faster adapta
or expensive to obtain. The article covers the state-of-the-art meta-learning approaches and explores the relationship betwee
the synergies between these topics and the field of meta-learning, the article demonstrates how advancements in one area ca
task distributions, unsupervised meta-learning, learning to efficiently adapt to data distribution shifts, and continual meta-le
of meta-learning and its potential impact on various machine learning applications. We believe that this technical overview

Alzheimer’s Disease (AD) accounts for the detection. Furthermore, we proposed a data augmentation
method to enlarge the dataset, designed an extra ERPNet
feature extract layer to extract multi-modal features and
used domain-adversarial neural network to improve the
performance of MCI diagnosis. We achieved an average
accuracy of 88.81% for MCI diagnosis and 100% for AD
diagnosis. The results of this paper suggest that our classification method can provide a feasible and affordable way
to diagnose dementia
majority of dementia, and Mild Cognitive Impairment (MCI)
is the early stage of AD. Early and accurate diagnosis of
dementia plays a vital role in more targeted treatments
and effectively halting disease progression. However, the
clinical diagnosis of dementia requires various examinations, which are expensive and require a high level of
expertise from the doctor. In this paper, we proposed a
classification method based on multi-modal data including
Electroencephalogram (EEG), eye tracking and behavioral
data for early diagnosis of AD and MCI. Paradigms with
various task difficulties were used to identify different
severity of dementia: eye movement task and resting-state
EEG tasks were used to detect AD, while eye movement
task and delayed match-to-sample task were used to detect
MCI. Besides, the effects of different features were compared and suitable EEG channels were selected for the

The eikonal equation has become an indispensable tool for modeling cardiac electrical activation accurately and efficiently.
manner. Nonetheless, the fitting procedure remains a challenging task. The present study introduces a novel method, Geode
reproduce a given ECG. We show that Geodesic-BP can reconstruct a simulated cardiac activation with high accuracy in a
the future shift towards personalized medicine, Geodesic-BP has the potential to help in future functionalizations of cardiac

In this paper, we focus on the problem of remote state estimation in wireless networked cyber-physical systems (CPS). Info
a denial of service (DoS) attack where one or more channels are jammed by an attacker transmitting spurious signals. The a
continuous action spaces. In addition, the state and action spaces have high dimensionality, and the channel states are not fu
a novel deep neural network (DNN) structure for detecting changes in the attack policy post-training. The proposed online p
featuring a DRL-based defender that is trained initially and adapts continually to changes in attack policy has been develop

AI-based Network Intrusion Detection Systems (NIDS) provide effective mechanisms for cybersecurity analysts to gain ins
atypical and dynamically changing (polymorphic) attacks. In this paper, we focus on improving detection capability of the I
detection of new attacks, specifically for minority attack samples in the input data. The employed attack quality analysis en
training it using the CICIDS2017 and CICIoT2023 benchmark datasets and evaluating its performance against several atyp
attacks with approximately 90% balanced accuracy for most of the cases, and surpasses various state-of-the-art detection an
Machine learning (ML) and deep learning (DL) advancements have greatly enhanced anomaly detection of network intrusio
suitable for offline traffic analysis, while packet-based NIDS can analyze traffic and detect attacks in real-time. Current pac
positives. Additionally, most literature-proposed packet-based NIDS capture only payload data, neglecting crucial informat
intelligence-enabled methodological framework for packet-based NIDS that effectively analyzes header and payload data a
detection model to process these images and detect malicious activities. Through experiments using publicly available big d

Otago Exercise Program (OEP) is a rehabilitation program for older adults to improve frailty, sarcopenia, and balance. Acc
(HAR) systems has lead to a revolution in healthcare. However, the use of such HAR systems for OEP still shows limited p
Inertial Measurement Unit (IMU). Two datasets were recorded, one in a laboratory setting, and one at the homes of the pati
sliding window; 2) based on stage 1, using a 6-second sliding window to recognize the OEP sub-classes. Results showed th
activities could be recognized with f1-scores over 0.8: ankle plantarflexors, abdominal muscles, knee bends, and sit-to-stan

Sequential pattern mining is a dynamic and thriving research field that aims to extract recurring sequences of events from c
as a vital necessity across various domains, e.g. medicine. Analyzing temporal event sequences within patients’ clinical his
mined graphs offer a significantly more expressive representation than mere event sequences, capturing intricate details of
world data comprising information about subjects suffering from sleep disorders. Alluring frequent complete event graphs w

On July 20, 2021, the northern Henan Province was hit by a historically rare, exceptionally heavy rainstorm (“7.20” Rainsto
overexploitation of groundwater since the last century has led to severe ground subsidence in the same area. We apply the i
recharge groundwater, the relationship between flood inundation, groundwater level change, and ground deformation is ana
there was a significant amount of subsidence mitigation and surface uplift across the region due to the groundwater recover
technical reference to similar circumstances.

The ice, cloud, and land elevation satellite-2 (ICESat-2) is the only satellite that produces photon-counting light detection a
with sub-surface signals. Conventional denoising methods applied to sea surface photon data of variable density involve the
which incorporates the Gaussian distribution of dual-signal peaks to determine the sea surface range. This method facilitate
variable parameters. The elevation error by DSUMP within 0.1m accounts for more than 97%. The mean absolute error is w
introduces a novel denoising technique for extracting sea surface elevation from ICESat-2 altimetry data, and its applicabili

Telemarketing is a well-established marketing approach to offering products and services to prospective customers. The eff
enterprise resources in vain while missing interested ones. The introduction of business intelligence and machine learning m
influential features and the construction of effective learning models for improved performance remain a challenge. Further
problem by creating biased and inaccurate models. Additionally, customer preferences are likely to change over time due to
in model retraining is maintaining a balance between stability (retaining older knowledge) and plasticity (being receptive to
accurately. A novel online learning method is proposed for model retraining when new samples are available over time. Th
the literature. Extensive experiments with real-world data show that the proposed approach achieves excellent re...

Earthquake-triggered landslides (ETLs) are characterized by their extensive occurrences, having wide distributions. The co
swift detection of ETLs. In this study, we introduce an ETLs extraction method (MAST) combining morphological analysis
to convolution neural networks, aiding in tasks such as target detection and semantic segmentation. To enhance the accurac
extract the features of landslide boundaries. It effectively addresses issues such as discretization and irregularization of the
the 2022 Ms 6.8 Luding Earthquake, we conducted automated extraction of ETLs utilizing the MAST model. Experimental
enhanced value in landslide extraction. Notably, it demonstrates a significant advantage in boundary extraction. Employing

Brain hemorrhage, a type of stroke caused by an artery in the brain bursting and causing localized bleeding in the surroundi
technologies. However, the accurate and rapid interpretation of these images remains challenging. This study explores a dee
Neural Networks (CNN) and Random Forests (RF). The results demonstrate the potential of these techniques in enhancing
In recent years, unmanned aerial vehicles (UAVs) have revolutionized various fields including agriculture, surveillance, an
their size and context variability. This project proposes an method leveraging YOLO v8, an advanced variant of the You On
detection accuracy. Firstly, a novel data augmentation strategy is employed to enrich the dataset and improve the model's ab
amidst complex backgrounds. Furthermore, a refined loss function is introduced to prioritize detection performance for den
performance in terms of detection accuracy and computational efficiency. The proposed framework not only enhances obje

Detection of landslides from remote sensing images is crucial for disaster management and environmental monitoring. This
object detection techniques with domain-specific enhancements to address the challenges inherent in landslide detection. M
annotated with landslide instances. Through extensive experimentation, LS-YOLO demonstrates superior performance in te
for disaster response and land management applications. LS-YOLO represents a significant advancement in the field of lan

Precipitation nowcasting refers to the prediction of small-scale precipitation events at minute and kilometer scales within th
their ability to effectively capture intricate and rapidly evolving precipitation patterns. To address this limitation, meteorolo
GAN-based prediction network (named FsrGAN). In the first stage, we design a satellite-radar fusion prediction network kn
multiscale features. In the second stage, we introduce a GAN-based network (FusionGAN) that further mines the compleme
region demonstrate the notably superior performance of our model in terms of image quality and precipitation forecasting m
using satellite and radar data effectively predicts convective initiation.

This study focuses on analysing user reactions to Facebook posts through a gender-based lens, employing advanced machin
The primary objective is to understand how male and female users react to Facebook comments, leveraging two sophisticat
The performance of these models is evaluated using standard metrics: accuracy, precision, recall, F1-score, and error rate.
This analysis has significant implications for social media platforms and marketers, enabling tailored content strategies that

The system presents a sophisticated deep learning approach for accurately determining eye blink completeness. Utilizing a

This hybrid model, combining convolutional neural networks (CNNs) for spatial feature extraction and long short-term mem

The Eye-LRCN algorithm is evaluated based on key performance metrics, including accuracy, error rate, and execution tim

The model predicts whether a blink has occurred and classifies the eye state into categories: open eye, closed eye, looking f

Internet of Things (IoT) devices has increased their vulnerability to Distributed Denial of Service (DDoS)

attacks. DDoS attacks have evolved into complex multi-vector threats that highvolume and low-volume attack strategies, po

importance of reliable detection and prevention measures. This paper introduces a novel Deep Ensemble

learning with Pruning (DEEPShield) system, to efficiently detect both high- and low-volume DDoS attacks

in resource-constrained environments. The DEEPShield system uses ensemble learning by integrating a

Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM)network with a network traffic analysis sys
accuracy algorithms

In the realm of financial forecasting, predicting stock prices is a highly challenging yet crucial task for investors and analys
explores the integration of Value-Weighted Skill Scores in a deep ensemble learning framework, which combines Lasso reg
mitigating over fitting. In parallel, LSTM, a type of recurrent neural network adept at capturing temporal dependencies, mo
This study emphasizes the improvement of generalization through a novel composite approach involving the use of a lifecy
public datasets to assess its generalization performance . The Attack is identified using CICIDS 2017 Dataset with using tha
detection challenges
This project is centered on developing a sophisticated admin-focused ID card management system utilizing Django. The sy
comprehensive management of employee records. Features include the ability to add, update, and delete employee details s
cards in both PDF and image formats. The system includes customizable templates, allowing for tailored designs to meet sp
process for managing employee data and producing ID cards. This automation enhances operational efficiency and accurac
Django's advanced capabilities, this project aims to improve the efficiency, accuracy, and security of ID card management,

An online auction system developed using Django framework facilitates a dynamic marketplace where administrators, vend
list products/services for auction, setting starting bids and auction durations. Bidders engage in competitive bidding, placing
vibrant and transparent online auction environment. Furthermore, the system incorporates features such as real-time notific
reporting tools to monitor platform performance, track key metrics, and identify trends, enabling informed decision-making
promoting fair competition, transparency, and efficiency, the Django-based online auction system establishes itself as a reli

This Hospital Management System, developed using Python Django, is designed to efficiently handle hospital records and
displaying available appointments with their details, and maintaining patient records. Patients can easily register and access
decision. Patients are required to provide details about their symptoms and can view their appointments and hospital bills th

The Agri Shop is a comprehensive online selling application designed specifically for farmers to enhance their market reach
fertilizers, and farming equipment. With an intuitive interface, farmers can easily create and manage their product listings,
allowing them to explore various agricultural products, compare prices, and make purchases directly from their devices. Th
platform includes features such as delivery scheduling and order tracking, which enhance convenience and reliability for bo
empowering farmers to reach a broader audience and improve their sales outcomes.

This project is centered on developing a sophisticated admin-focused ID card management system utilizing Django. The sy
comprehensive management of employee records. Features include the ability to add, update, and delete employee details s
cards in both PDF and image formats. The system includes customizable templates, allowing for tailored designs to meet sp
process for managing employee data and producing ID cards. This automation enhances operational efficiency and accurac
Django's advanced capabilities, this project aims to improve the efficiency, accuracy, and security of ID card management,

The Therapist Chatbot for Medical Assistance is a cutting-edge application developed using the Django framework, designe
offering preliminary medical advice, symptom analysis, and mental health support based on user inputs. Integrated into a D
system's robust backend, built with Django, ensures secure handling of user data and scalability to accommodate a growing
managing their health and well-being effectively.

The Django-Parking Management System utilizing YOLO (You Only Look Once) represents an advanced solution for opti
algorithm, to monitor and manage parking spaces effectively by identifying and tracking vehicles as they enter and exit par
processes. Through the integration of YOLO, the system can accurately detect and classify vehicles, providing dynamic upd
receive notifications about space availability. Additionally, the backend system, powered by Django, ensures secure data m
with the comprehensive management features of Django, this system enhances the efficiency and convenience of parking m

Online Complaints Portal using Django and Python is a comprehensive web application designed to facilitate the submissio
various issues, ranging from service-related grievances to product defects. Users can easily submit detailed reports, attach r
complaint routing, assignment to appropriate departments, and timely notifications to users about updates and resolutions. T
the complaints process and enhancing transparency, the Online Complaints Portal helps organizations improve customer sa

Benefit Bot is an advanced chatbot application developed using the Django framework, designed to facilitate seamless acce
information and guidance on various government programs. Through a user-friendly web interface, Benefit Bot allows indi
framework ensures a robust backend, handling secure user data management, authentication, and efficient querying of a com
deadlines. By integrating these functionalities, Benefit Bot enhances public access to essential services, simplifies the appli
Ride Rentals using Django and Python is a sophisticated web application designed to streamline the process of renting vario
vehicle details, and book rides with ease.The application features a user-friendly interface where customers can search for v
manages user accounts, booking schedules, payment processing, and vehicle inventory, ensuring secure and efficient opera
manage listings, track bookings, and handle payments. By integrating Django’s robust security measures and Python’s data

Meal Metric Detection and Calorie Estimation is a sophisticated web application developed using the Django framework, d
the content of meals from photos uploaded by users. By utilizing state-of-the-art computer vision techniques, the system ide
handling of user data, seamless integration with image recognition models, and the ability to manage extensive databases o
their health goals and preferences. Additionally, the application offers features such as meal logging, historical data trackin
users to make informed dietary choices and maintain a balanced and healthy lifestyle.

Blockchain-Based Voting System using Django is a cutting-edge web application that integrates blockchain technology to e
that each vote is encrypted and securely recorded on a blockchain ledger. This decentralized and immutable ledger ensures
unalterable record of votes, safeguarding the electoral process. This combination of technologies ensures a reliable and tran

A Built-in Quality Report Maintenance System Using Blockchain and Data Science is an innovative Django-based applicat
recording and tracking quality reports, ensuring that all data entries, modifications, and historical changes are securely logg
improvement. Users can generate comprehensive quality reports, visualize performance trends through interactive dashboar
science algorithms offer actionable intelligence to drive continuous quality improvements. This combination of blockchain
making.

Question Bank Recommendation and Online Examination by Dual Mode Operation System is a sophisticated application th
questions from an extensive repository based on specific exam requirements, utilizing advanced algorithms to match questi
responses, detect patterns, and provide detailed performance insights. This integration enhances the customization and scala

A Session of Multi-Task Manager for File Converter is a versatile application designed to efficiently handle the conversion
across different formats such as PDFs, images, documents, and audio files. The system provides a user-friendly interface w
conversions in parallel, significantly reducing the time required compared to sequential processing. The application ensures
enhances productivity and efficiency, making it an indispensable tool for users who need to handle large volumes of file co

AI-Generated Color Formula in the Paint Industry using Python and Django is a sophisticated web application designed to r
precise color recipes based on user inputs such as desired color attributes, base materials, and existing color databases. The
to develop predictive models that analyze historical color data, optimize mixing ratios, and ensure that the final product me
consistency. This approach reduces human error, accelerates production timelines, and supports the creation of high-quality

Portfolio Website in Python Using Django is a dynamic and customizable web application developed with the Django fram
managing a personalized portfolio, featuring sections for showcasing work samples, detailing professional experiences, and
and documents. The application provides an intuitive admin interface for content management and customization, allowing
unauthorized access and potential vulnerabilities. By leveraging Django’s flexibility and scalability, the portfolio website d
clients, employers, or collaborators.

Real Estate Listings Website built using Python Django is a sophisticated web application designed to facilitate the buying,
advanced search capabilities, and user interaction. Using Django’s powerful backend, the application supports the creation
location, price range, and property type, while also viewing interactive maps and virtual tours. The application includes fea
framework, the website ensures reliable performance and data protection, providing an efficient and user-friendly platform

YouTube: Statistical Analysis Tool developed using Django and Python is an advanced web application designed to provid
comprehensive understanding of their channel's performance. The application integrates with the YouTube Data API to gat
comparative analyses, and key performance indicators. The tool also features advanced data filtering and segmentation opti
this application empowers content creators and marketers to make data-driven decisions, optimize their content strategy, an

DjangoMart: Online Marketplace is a feature-rich web application developed using Django, designed to facilitate a seamles
transactions, and handling customer interactions. Vendors can create and manage their storefronts, upload product details, s
purchases with ease. DjangoMart incorporates secure payment gateways, user authentication, and order tracking to ensure a
and buyers. By leveraging Django’s robust framework, DjangoMart delivers a scalable and customizable solution for buildi
E-Learning Platform using Django and Python is a comprehensive web application designed to facilitate online education a
management, and student engagement. The application enables educators to create and manage courses, upload learning ma
handles user authentication, data management, and real-time updates, ensuring a seamless learning experience. The platform
Django’s secure and scalable architecture, the E-Learning Platform delivers a reliable and engaging online learning environ

E-Commerce Website for Visually Impaired developed using Django is a highly accessible web application designed to pro
can navigate, browse, and shop effectively. The application utilizes Django's robust backend to manage product listings, us
controlled navigation, text-to-speech functionality, and customizable display options to enhance readability. The website al
items, add products to their cart, and complete purchases with accessible forms and controls. Django's secure framework en
and empowering online shopping experience for visually impaired users, promoting equal access to digital retail opportunit

Online Paying Guest Accommodation Project using Django is a comprehensive web application designed to facilitate the se
intuitive search interface. Landlords and property managers can list their accommodations, providing detailed descriptions,
accommodations directly through the platform. The application also includes features for user authentication, secure payme
seeking temporary housing and landlords looking to manage their properties efficiently.

Advanced Employee Management System using Django is a powerful web application designed to optimize and streamline
and payroll processing, all managed through an intuitive interface. Leveraging Django's robust backend capabilities, the app
employee metrics, generate detailed reports, and support strategic decision-making. By providing a seamless and user-frien

Industrial Visit Planning & Booking System using Python is a sophisticated web application designed to streamline the org
facilities, allowing institutions or companies to explore and book tours based on their specific needs and preferences. Users
booking confirmations, and notifications. It also includes features for tracking visitor information, managing facility capaci
and industrial entities, and provides a seamless experience for users looking to organize educational and professional indus

Software Recommendation by AI Machine Learning is a dynamic application developed using Python Flask, designed to pr
requirements, and individual preferences, to recommend software solutions that best fit their criteria. The Flask framework
employs techniques like collaborative filtering, content-based filtering, and hybrid models to generate accurate and relevan
detailed descriptions and user reviews. The system continuously learns and adapts from user feedback and interactions, imp
find the most suitable tools for their needs and thereby streamlining decision-making in software acquisition.

Customer Relationship Management (CRM) by Sentiment Analysis using AI Technology is a sophisticated approach design
reviews, and communications to gauge sentiment and emotional tone. The AI-powered sentiment analysis tool processes la
satisfaction trends, and respond proactively to concerns. Python-based libraries like NLTK and SpaCy facilitate natural lang
to tailor their customer service approaches, address issues promptly, and improve overall engagement. By incorporating sen

Statistics and Visualization of Data Analytics in Social Media App Data is a powerful application developed using Python F
platforms, including metrics like user engagement, sentiment analysis, and content trends. Leveraging Flask's lightweight a
an intuitive web interface that displays interactive visualizations such as charts, graphs, and heatmaps, enabling users to exp
campaigns in real time. Additionally, the application supports data filtering and segmentation, allowing users to drill down
data-driven decisions, optimize social media strategies, and gain a deeper understanding of their audience's behavior and pr

A Taste of Tea is a sophisticated web application developed using Python Flask, designed to enhance customer experiences
one for customer interaction. In the first stage, coffee shop managers can use the Flask-based backend to configure and man
analyze customer preferences and historical sales data, helping managers optimize their inventory and tailor their product re
the second stage, customers interact with the application through an engaging web interface. They can browse the coffee sh
valuable feedback to the coffee shop. Based on individual preferences and past interactions, the application offers personali
tailored recommendations and interactive reviews but also provides coffee shop managers with the tools and insights neede
Task Scheduling and Productivity Sheet Security using blockchain technology and Python Flask is an advanced application
schedules and productivity metrics, ensuring that all changes and updates are securely logged and verified. The application,
and productivity data are recorded on a blockchain ledger, which guarantees the integrity and transparency of the informati
schedules are protected from unauthorized changes and fraudulent activities. Users can access the application to create and
user authentication, access control, and blockchain interactions, enabling secure and efficient operations. By combining blo
productivity data against tampering and unauthorized access, ultimately fostering a more secure and trustworthy work envir

Step into Success: A Student Performance Analysis for Future Scope using Python Flask is a sophisticated web application
such as Pandas, Scikit-learn, and TensorFlow, to process and analyze historical student performance data, including grades,
in student performance, offering insights into areas of strength and opportunities for improvement. It generates detailed rep
application supports the creation of tailored educational plans and interventions, enhancing the overall effectiveness of acad

Beauty Sketchy is an innovative Flask-based web application that transforms photos into artistic sketches using Python. Th
artistic way to enhance their photos. The Flask framework serves as the backbone of the app, enabling seamless image uplo
artistic effect. The application leverages Python's powerful libraries for image manipulation and machine learning, ensuring
beautiful, customized sketches from their photos, making it a valuable resource for both personal and professional creative

URL Shortener with Phishing Attack Detection is a Flask-based web application designed to provide users with a secure an
validate URLs before they are shortened, ensuring that users are safeguarded from malicious sites and deceptive links. Whe
handles the backend operations, including URL shortening, data management, and the implementation of security protocols
shortening functionality with proactive phishing detection ensures a safer browsing experience, making it a valuable tool fo

Flipkart Reviews Extraction and Sentiment Analysis is a Flask-based web application designed to extract and analyze custo
then utilizes natural language processing (NLP) and sentiment analysis algorithms to evaluate the sentiment expressed in ea
terms to retrieve relevant reviews. The sentiment analysis component categorizes reviews into positive, negative, or neutral
advanced sentiment analysis, the application provides actionable insights for both consumers looking to make informed pur

Medical Assist: Doctor-Patient Appointment System using Python and Flask is a comprehensive web application designed
preferred doctors, view available time slots, and receive confirmation notifications. The Flask framework, known for its sim
process appointment data, ensuring real-time updates and accurate scheduling. The application features functionality for do
shows and improving overall appointment management. By integrating these capabilities, Medical Assist enhances the effic

IPL Score Prediction with Flask App Using Python is an innovative web application designed to forecast cricket match scor
application integrates machine learning models to analyze historical match data, player statistics, and other relevant factors
conditions, to generate score predictions. The backend of the Flask app processes these inputs, runs them through trained pr
predictions. With features like interactive dashboards and visualizations, users can easily explore different scenarios and un
data-driven predictions and strategic decisions.

SBERT: Sentence-BERT for Text Summarization is a Flask-based web application that utilizes Sentence-BERT (SBERT) t
input text to create meaningful summaries while preserving key information and context. The Flask framework supports the
the application swiftly generates summaries that capture the essence of the content. By integrating SBERT's deep learning m
text into accessible and actionable insights.

Corruption: Complaint Assist System is a Flask-based web application designed to streamline the reporting and managemen
and addressed efficiently. Users can fill out detailed complaint forms, attach relevant evidence, and track the status of their
measures to protect sensitive information. The system also includes features for complaint categorization, automated notific
unethical behavior confidently and supports authorities in addressing and resolving issues of corruption effectively.

OSTR: Online Survey Tool and Review is a robust Flask-based web application designed to facilitate the creation, distribut
time. The Flask framework provides a solid backend for managing survey data, user submissions, and real-time analytics. U
includes features for generating detailed reports and visualizations, enabling users to analyze survey results and review feed
organizations seeking to gain insights and improve decision-making through data-driven surveys and reviews.
Equip Yourself: Expense Tracker is a powerful Flask-based web application designed to help users manage and monitor the
their budget in real time. Utilizing Flask's robust backend capabilities, the app securely handles user data, enabling features
spending patterns. The application also includes tools for generating detailed reports and exporting data for further analysis
efficiently, and achieve better control over their personal finances.

FlaskHRM: Human Resource Management System is an advanced web application developed with Python Flask, designed
payroll, and handling recruitment processes. The Flask framework serves as the backbone of the application, offering a secu
application also supports automated notifications and reporting, enabling HR professionals to generate detailed reports on e
workforce management, making it an essential tool for organizations looking to optimize their human resources processes.

Event Planning and Management using Flask is a sophisticated web application designed to streamline the organization and
scheduling, and managing events. Users can effortlessly set up event details, such as date, time, location, and agenda, while
ensuring efficient coordination. Additionally, it integrates with calendar systems and provides tools for budgeting, vendor m
platform that simplifies event coordination and enhances the overall event experience.

Legal Document Automation Platform developed using Python and Django is an innovative web application designed to str
of various legal documents, such as contracts, agreements, and forms. Users can input specific data or select predefined tem
allowing users to insert variable fields, clauses, and conditional content based on their requirements. Additionally, it includ
backend with advanced document automation capabilities, this platform enhances efficiency in legal processes, improves co

Buy One Get One (BOGO) Offer Tracking System using Flask is a web application designed to efficiently manage and trac
promotions. The system allows users to set up various BOGO campaigns, specifying product details, promotional periods, a
management of promotional data, tracks redemption rates, and ensures accurate application of discounts. Additionally, the
engagement. By leveraging Flask's flexible framework, the BOGO offer tracking system provides a user-friendly and reliab

In this project, we present BoNuS, a novel approach for nuclei segmentation leveraging boundary mining with partial point
conversion, adaptive histogram equalization, and median filtering, to improve image quality and contrast. Subsequently, we
(IoU) and Dice coefficient, which provide insights into the overlap and accuracy of the predicted masks compared to the gr
image. The BoNuS framework demonstrates robust performance in segmenting nuclei, even with limited annotations, maki
which is essential for nodule morphological analysis. Nevertheless, most existing methods depend on extensive and precise

annotations by domain experts, which are labor-intensive and

time-consuming. In this study, we suggest using simple aspect

ratio annotations directly from ultrasound clinical diagnoses

for automated nodule segmentation. Especially, an asymmetric

learning framework is developed by extending the aspect ratio

annotations with two types of pseudo labels, i.e., conservative

labels and radical labels, to train two asymmetric segmentation

networks simultaneously. Subsequently, a conservative-radicalbalance strategy (CRBS) strategy is proposed to complemen

combine radical and conservative labels. An inconsistency-aware

dynamically mixed pseudo-labels supervision (IDMPS) module

is introduced to address the challenges of over-segmentation

and under-segmentation caused by the two types of labels. To

further leverage the spatial prior knowledge provided by clinical

annotations, we also present a novel loss function namely the clinical anatomy prior loss. Extensive experiments on two cli

collected ultrasound datasets (thyroid and breast) demonstrate

the superior performance of our proposed method, which can

methods take uncompressed dark images as inputs and achieve

great performance. However, in practice, dark images are often

compressed before storage or transmission over the Internet. Current methods get poor performance when processing comp

dark images. Artifacts hidden in the dark regions are amplifed

by current methods, which results in uncomfortable visual effects

for observers. Based on this observation, this study aims at

enhancing compressed dark images while avoiding compression

artifacts amplifcation. Since texture details intertwine with compression artifacts in compressed dark images, detail enhance

and blocking artifacts suppression contradict each other in image

space. Therefore, we handle the task in latent space. To this end,

we propose a novel latent mapping network based on variational

auto-encoder (VAE). Firstly, different from previous VAE-based

methods with single-resolution features only, we exploit multiple

latent spaces with multi-resolution features, to reduce the detail

blur and improve image fdelity. Specifcally, we train two multilevel VAEs to project compressed dark images and normal-l

images into their latent spaces respectively. Secondly, we leverage

a latent mapping network to transform features from compressed

dark space to normal-light space. Specifcally, since the degradation models of darkness and compression are different from
Anomaly detection (AD) in medical pictures identifies aberrant inputs based on normal training examples. Knowledge disti
architectures (S-Nets). This article proposes a T-S model with skip connections (Skip-TS) trained using direct reverse KD (
randomly initialized decoder (S-Net). In our base paper use different type of dataset for checking the segmentation model h
encoder and decoder using the up sampling and down-sampling model. Next step is to fit the model with the train and test i

The Smart Traffic Management System using cloud computing aims to enhance urban traffic flow and reduce congestion th

The system begins by processing vehicle images from a dataset, performing pre-processing tasks like resizing and grey-sca
detection model using YOLO.

Traffic density is computed based on vehicle counts per unit length and sent to a cloud server for storage. The server furthe

The system’s performance is quantified through metrics such as accuracy and error rate, and results are presented in compa

This project delves into the potential of using deep learning to enhance the diagnosis of Autism Spectrum Disorder (ASD).
Networks (CNNs) and transfer learning, to analyze fMRI data from the Autism Brain Imaging Data Exchange (ABIDE) dat
learning could serve as a valuable tool for ASD diagnosis. We also aim to evaluate the model by calculating its accuracy, p

Accurate segmentation of kidney tumors is crucial for diagnosis, treatment planning, and monitoring of kidney tumour. Con
segmentation tasks. In this study, we propose a CNN-based approach for the segmentation of kidney tumors from abdomina
that first localizes the kidney region and then segments the tumor within the kidney. The accurate and robust segmentation
and monitoring of kidney cancer, ultimately improving patient outcomes.
In the realm of underwater photography, the quest to overcome challenges related to limited visibility and color distortion h
hybrid networks. The primary workflow involves the enhancement of low-light underwater images through the application
Subsequently, the dataset undergoes a split of 80:20 ratio, introducing variability. The pivotal stage employs CNN for class
study culminates in the evaluation of model performance, elucidated by accuracy and loss metrics, advancing the understan

This study introduces a novel approach utilizing Support Vector Machines (SVM) and Convolutional Neural Networks (CN

The proposed system leverages SVM for feature extraction and classification, complemented by CNNs for deep learning-ba

The effectiveness of the approach is validated through rigorous experimentation on a dataset of kidney disease images, dem

This research contributes to advancing medical imaging technology by providing a feasible and efficient tool for early detec

In image preprocessing, the a facial regionof interest has been segmented from the input image.with using classical deep fe
system has attained a faster training approach using the proposed quantum convolutional neural network approach that take
proposed that analyzes static, sequential, or video facial images from medical healthcare data to detect emotions in people’s
metrics such as accuracy, precision and recall.

Automatic retinal layer segmentation with medical images, such as optical coherence tomography (OCT) images, serves as
the algorithm should be light-weight to be deployed for practical clinical applications. Therefore, it is desired to design a lig
our approach follows an encoder-decoder structure, where the encoder part employs multi-scale feature extraction and a Tra
multi-scale asymmetric attention (MAA) module for preserving the semantic information at each encoder scale. The experi
other public datasets, with only 3.3M parameters.

In this study, we explore the application of deep omni-supervised learning techniques for the detection of rib fractures from

The primary objective is to accurately identify regions of rib fractures and predict their affected status using deep neural ne
fracture characteristics.

By leveraging deep omni-supervised learning, which combines labeled, unlabeled, and weakly labeled data, we aim to enha

The proposed approach harnesses the hierarchical features learned by models like ResNet or MobileNet, enabling effective

Drowsiness of drivers is one of the main reasons behind road accidents. It is natural for the drivers who take long drives to
ensuring safety in various domains, such as driving, aviation, and industrial operations. This paper presents a deep learning
network (CNN) specifically designed for analyzing facial features and eye positions. LAnet leverages advancements in ima
from images.Our method involves several stages: image loading, pre-processing, feature extraction, and classification. The
various states of alertness, enabling it to learn and indicate of drowsiness.

In recent years, the application of machine learning in the field of traffic management has gained significant attention, parti
road safety and traffic flow efficiency. The proposed system integrates multiple stages: accident detection, precise segment
accidents. Techniques such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are utilized to
interest within the scene. This involves using advanced image processing techniques and neural networks to delineate the a
are trained on historical data, considering various factors such as accident severity, time of day, and weather conditions. Th

In the rapidly evolving landscape of Internet of Things (IoT) environments, securing face recognition systems against unau

This paper proposes enhanced biometric template protection schemes aimed at ensuring the integrity and privacy of facial r

The objective is to develop a robust system capable of accurately determining whether a detected face is authorized. This is
2D facial analysis.

Once the face's authorization status is determined, the system extracts pertinent biometric information, encrypts it using RS
sensitive information from unauthorized disclosure.
Enhancing underwater images poses significant challenges due to issues like poor white balance, low contrast, and non-uni

By incorporating advanced techniques such as white balance correction, contrast adjustment, and histogram equalization, D
Short-Term Memory (LSTM) networks.

The CNNs are employed to capture and refine the spatial features of the image, while the LSTMs handle the temporal depe

This hybrid algorithm not only corrects color distortions and enhances contrast but also normalizes the image histogram, pr

The AIROGS challenge focuses on enhancing the accuracy and robustness of glaucoma screening through advanced artifici

Our approach leverages the power of two state-of-the-art convolutional neural network architectures: ResNet and MobileNe
imaging datasets.

This synergy enhances the robustness of the screening process, ensuring reliable detection across diverse populations and v

Our solution also incorporates advanced pre-processing techniques and data augmentation to improve generalization and re

Device-free human activity recognition plays a pivotal role in wireless sensing. However, current systems often fail to acco
recognition system integrated with a transmissive reconfigurable intelligent surface (RIS). TRTAR eliminates the necessity
transmitter or receiver without modifying the inherent hardware structure. Experimental results demonstrate that TRTAR at

The integration of Computer-Aided Diagnosis (CAD) with Large Language Models (LLMs) presents a promising frontier i
potential of this integration, current works face at least two limitations: (1) From the perspective of a radiologist, existing st
undermine the quality and reliability of the generated medical reports. (2) Current LLMs lack the requisite depth in medica
ChatCAD+, to be universal and reliable. Specifically, it is featured by two main modules: (1) Reliable Report Generation an
hierarchical in-context learning. Concurrently, the interaction module leverages up-to-date information from reputable med
reliability for interpretation and advice. The source code is available at GitHub.

Automated colorectal cancer (CRC) segmentation in medical imaging is the key to achieving automation of CRC detection,
enormous potential because of its broad implementation, superiority for the hollow viscera (colon), and convenience withou
colorectum from other structures with similar appearance and distinguishing the CRC from the contents of the colorectum.
aware deep learning-based approach, which builds a novel 1-D colorectal coordinate system and encodes each voxel of the
topology into the segmentation network and thus improve the colorectum’s continuity. Self-attention layers are utilized to c
introduced to leverage a large amount of unlabeled data to improve segmentation performance. We validate the proposed ap
segmentation methods and achieves the segmentation accuracy in DSC for CRC of 0.669 and colorectum of 0.892, reaching

Contour-based instance segmentation has been actively studied, thanks to its flexibility and elegance in processing visual o
algorithm, the proposed PolySnake achieves superior and robust segmentation performance with an iterative and progressiv
progressively deformed toward the object boundary. At each iteration, PolySnake builds a semantic-rich representation for
encloses the object instance. Beyond the scope of general instance segmentation, extensive experiments are conducted to va
PolySnake outperforms the existing advanced methods on several multiple prevalent benchmarks across the three tasks. Th

This article proposes crack segmentation augmented by super-resolution (SR) with deep neural networks. In the proposed m
results. For realistic scenarios, the SR network is extended from nonblind to blind for processing a low-resolution (LR) ima
experiments with state-of-the-art (SoTA) segmentation methods demonstrate the superiority of our joint learning, and vario

Automatic retinal layer segmentation with medical images, such as optical coherence tomography (OCT) images, serves as
the algorithm should be lightweight to be deployed for practical clinical applications. Therefore, it is desired to design a lig
approach follows an encoder-decoder structure, where the encoder part uses multiscale feature extraction and a transformer
asymmetric attention (MAA) module for preserving the semantic information at each encoder scale. The experiments show
public datasets, with only 3.3 M parameters.
Referring image segmentation (RIS) is a fundamental vision-language task that intends to segment a desired object from an
fine-grained vision-language alignment or lack required dense alignment, resulting in scalability issues or mis-segmentation
with self-distillation and propose a novel cross-modality masked self-distillation framework named CM-MaskSD, in which
Moreover, our CM-MaskSD framework can considerably boost model performance in a nearly parameter-free manner, sinc
features. Comprehensive experiments on three benchmark datasets (i.e. RefCOCO, RefCOCO+, G-Ref) for the RIS task co

The precise recognition of food categories plays a pivotal role for intelligent health management, attracting significant rese
Nevertheless, these datasets are well-curated from canteen scenarios and thus deviate from food appearances in daily life. T
two new benchmarks, namely DailyFood-172 and DailyFood-16, specifically designed to curate food images from everyda
simple yet effective baseline method named Multi-Cluster Reference Learning (MCRL) to tackle the aforementioned doma
MCRL can be seamlessly coupled with existing approaches, yielding non-trivial performance enhancements. We hope our

Fairness (also known as equity interchangeably) in machine learning is important for societal well-being, but limited public
To address this gap, we introduce Harvard Glaucoma Fairness (Harvard-GF), a retinal nerve disease dataset including 3,300
glaucoma prevalence than other races. We also propose a fair identity normalization (FIN) approach to equalize the feature
fairness tasks with 2D and 3D imaging data, demonstrating the utilities of our dataset Harvard-GF for fairness learning. To
of fairness. The dataset and code are publicly accessible via https://ophai.hms.harvard.edu/datasets/harvard-gf3300/ .

In the remote sensing community, extracting buildings from remote sensing imagery has triggered great interest. While man
depth review of both early efforts and recent advances, which are aimed at extracting geometrical structures or semantic att
building change detection, and annotation data correction. Furthermore, a list of corresponding benchmark datasets is given

In recent years, deep learning has emerged as the dominant approach for hyperspectral image (HSI) classification. Howeve
of pixels per scene is costly and time consuming. In this article, we tackle the problem of few-shot HSI classification by lev
augmentations tailored for natural imagery to generate positive pairs. However, these augmentations are not directly applic
HSIs. The proposed strategies mitigate the need for high-quality data augmentations, providing an effective solution for few
we conduct a thorough analysis of the impact of data augmentation in contrastive learning, highlighting the advantage of ou

Collaborative representation (CR) models have been widely used in hyperspectral image (HSI) classification tasks. Howeve
weighted CR classification model (MWCRC) based on the joint spatial-spectral data. It imposes mean and weighted constra
principle of minimizing the representation residuals is proposed. Sample augmentation is realized through initial classificat
spatial homogeneity and heterogeneity, the extended morphological profile (EMP) and the stacking approach are utilized to
samples in three real datasets.

Lossless data hiding in ciphertexts (LDH-CT) is to perform data embedding without changing their plaintexts, which can be
(PM) are proposed for the “N-th Degree Truncated Polynomial Ring Unit” (NTRU) scheme, respectively. In the PE algorith
dozens of bit values can be extracted from it. Moreover, the PE algorithm can be combined with a polynomial partitioning s
by selectively sampling a polynomial to match the to-be-hidden value. Furthermore, the data hidden with the PM algorithm
are implemented and compared with several schemes developed for NTRU, BGN, LWE and Paillier encryption. Experimen

The deployment of automated deep-learning classifiers in clinical practice has the potential to streamline the diagnosis proc
interpretability, while interpretable models do not have competitive classification accuracy. In this paper, we introduce a ne
interpretable prototype-based classifier (ProtoPNet) and the teacher is an accurate global image classifier (GlobalNet). The
GlobalNet learns from ProtoPNet’s classification performance and pseudo labels. This reciprocal learning paradigm enable
retinal disease diagnosis. Moreover, relying on weakly-labelled training images, InterNRL also achieves superior breast can

Diffusion models with continuous stochastic differential equations (SDEs) have shown superior performances in image gen
sampled in fast MR imaging, while existing diffusion models are performed throughout the entire image or k -space, inevita
reconstructions. To address these challenges, we propose a novel SDE tailored specifically for MR reconstruction with the
reverse diffusion. Experiments conducted on the publicly available fastMRI dataset demonstrate that the proposed HFS-SD
properties are also confirmed through theoretical and experimental validation. Our code and weights are available at https:/
Interpretability is highly desired for deep neural network-based classifiers, especially when addressing high-stake decisions
which one to choose. To address this problem, a novel decision-theory-inspired approach is investigated to establish a self-i
layer fully connected network with unity weights. The model is trained to estimate the test statistic of the given trained blac
image that, when processed by the fixed fully connected layer, produces the same test statistic value as the original classifie
contributions. Unlike the traditional post-hoc interpretability methods, the proposed method is self-interpretable, quantitativ

Auroral classification plays a crucial role in polar research. However, current auroral classification studies are predominant
low classification rates for complex auroral patterns. Furthermore, existing studies employing traditional machine learning
classification network, MLCNet, based on a multiview approach. First, we develop a lightweight feature extraction backbon
design a novel multiscale reconstructed feature module. Finally, to highlight the discriminative information between aurora
2003–2004. The experimental results demonstrate that the fusion of multiwavelength information significantly improves th
multiview methods in terms of both accuracy and computational efficiency.

Ultrasound localization microscopy (ULM) allows for the generation of super-resolved (SR) images of the vasculature by p
prolonged acquisition times and high frame rates. The primary goal of our study is to relax the requirement of high frame ra
Functions (RBFs) as interpolators to estimate the missing values in the 2-dimensional (2D) spatio-temporal structures. To e
data to the original frame rate using the suggested interpolation to reconstruct the missing frames. Finally, using both the or
A), a Rat kidney (dataset B), a Rat tumor (dataset C) and a Rat brain bolus (dataset D), interpolating at the in-phase and qua
proposed technique is successful in reconstructing accurate SR images while requiring frame rates of one order of magnitud

Feature extraction and accurate classification are crucial tasks in the land-cover classification of the hyperspectral image (H
deep features are extracted using RPNet that requires no pretraining stage. In addition to the obtained feature set, the origin
structure of the data. The high-dimensional feature sets are then processed by a linear discriminant analysis (LDA) to increa
generate pseudosamples. In the final stage, the reduced-dimension feature sets are classified by the use of superpixel-guided

Exploiting spectral–spatial information and reducing the number of required training samples are important for improving t
samples while improving the classification performance. To improve classification performance, the proposed ALSSC emp
refined by guided filtering and subsequently employed as the input for the next round of classification. To reduce the dema
the effectiveness of the proposed ALSSC, experiments are conducted using a tree species classification dataset collected by
improvement of 11.62%. In addition, trained with fewer labeled samples, the ALSSC outperforms state-of-the-art spectral–

This article studies the distributed fusion estimation (DFE) issue for networked multi-sensor systems (NMSSs) with stochas
characterized by multiplicative noises. For reducing the communication burden, local estimation signals are subject to dime
dimensionality reduction strategy is designed from the defender's point of view in the sense of minimum fusion error covar
estimation algorithm (DKFEA) is proposed. The stability conditions making the mean square error (MSE) for DFE bounde

Estimating the head pose of a person is a crucial problem for numerous applications that is yet mainly addressed as a subtas
address the issue of ambiguous rotation labels by introducing the rotation matrix formalism for our ground truth data and pr
current state-of-the-art. Together with new accumulated training data that provides full head pose rotation data and a geode
method significantly outperforms other state-of-the-art methods in an efficient and robust manner, while its advanced predi

Establishing and maintaining farmland geometric boundaries is crucial to increasing agricultural productivity. Accurate fiel
agricultural field plots are geofenced into their individual field geometric boundaries. This paper presents a novel coordinat
can solve for challenging field-to-field segmentation cases where the operator engages the towed implement continuously a
coordinate data is plotted and image processing techniques are applied to erode any pathway(s) that may present in job sites
The algorithm was validated against two unique machinery implement datasets, which combined, contain a mixture of 296
proposed algorithm is deterministic and does not require any additional labor, land traversal or aerial surveillance to produc

Since the onset of the COVID-19 pandemic in 2019, many clinical prognostic scoring tools have been proposed or develop
making. In this article, we present a new image explainability method named ensemble AI explainability (XAI), which is ba
19 respiratory infected patients. In addition, we surveyed the existing literature and compiled prevailing quantitative and qu
Grad-CAM++). Our quantitative experimental results have shown .
Edge computing enables rapid data processing and decision-making on satellite payloads. Deploying deep learning-based te
proposes an edge-computing-enabled inference model specifically designed onboard satellites. The proposed model follows
consumption with a single-precision floating-point format, the edge-computing-enabled inference model proposes a quantiz
model) but also has a similar quality with the low-light enhanced in full-precision computing of lightweight training model

Object detection in unmanned aerial vehicle (UAV) images is an important and challenging task for many applications, wh
small objects in UAV images. Specifically, 1) kernel K-means is used to obtain optimal anchors for dense and small object
proposed to improve the receptive field of the network and to reduce the number of network parameters; and 4) a small dete
VisDrone-2019, LEVIR-ship, and Stanford Drone datasets show that our method not only has higher detection accuracy bu

Hyperspectral image classification (HSIC) has become a hot research topic. Hyperspectral imaging (HSI) has been widely u
obtained spectral data and the correlating HSI data object, generate efficient classification results that are complex for tradi
challenges. This motivates using DL for HSIC, which shows promising results. This survey provides a brief description of D
addressing these issues. In this article, we divide state-of-the-art DL methodologies and DL with ensemble into spectral fea
Furthermore, we will take into account that DL involves a substantial percentage of labeled training images, whereas obtain
future recommendations.

Hitherto, image-level classification on remote sensing landslide images has been paid attention to, but the accuracy of tradi
challenges that hinder the lead-in of this theory in deep landslide image classification. Aiming at the three problems, this st
couple the evidence theory with deep remote sensing landslide image classification, a channelwise multiscale visual salienc
evidence-theoretic fusion process, we design an interpretability improved three-branched fusion. Experiments on Bijie Land
scene classifiers, evidence fusion algorithms, and versatile evidence-theoretic deep learning classifiers. We also evaluated t

Precipitation nowcasting refers to the prediction of small-scale precipitation events at minute and kilometer scales within th
their ability to effectively capture intricate and rapidly evolving precipitation patterns. Thus, meteorological satellite is cons
(named FsrGAN) is proposed. In the first stage, we design a satellite-radar fusion prediction network known as FsrNet. Thi
the second stage, we introduce a GAN-based network (FusionGAN) that also mines the complementary information of sate
exhibit the notably superior performance of our model in terms of image quality and precipitation forecasting metrics in com
satellite and radar data demonstrates the ability to predict convective initiation.

Large volumes of used electronics are often collected in remanufacturing plants, which requires disassembly before harvest
observe work environments and recognize human actions accurately. Rich activity video recording and supervised learning
video-based human activity recognition. The framework consists of two main elements: 1) a variational-autoencoder-based
labels; here, we use a case study of disassembling a hard disk drive. The framework shows an average recognition accuracy

Brain hemorrhage refers to a potentially fatal medical disorder that affects millions of individuals. The percentage of patien
clinical practice. A Computed Tomography Image has frequently been employed for the purpose of identifying and diagnos
dedication. In the most recent studies, a variety of techniques rooted in Deep learning and traditional Machine Learning hav
by utilizing Machine Learning and Deep Learning. This research focuses on the main stages of brain hemorrhage, which in
are utilized for the analysis of the detection process. A detailed comparison of performances is analyzed. Moreover, this pa

Objective: Identifying mild cognitive impairment (MCI) subjects who will progress to Alzheimer's disease (AD) is not only
conversion from magnetic resonance images. Methods: We propose a novel grading biomarker for the prediction of MCI-to
and the selection of training data. Based on the studies of these factors, a grading biomarker is then calculated for each MC
Results: Using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, the proposed global grading biomarker ac
classification AUC further increases to 84-92% when age and cognitive measures are combined with the proposed grading
removal of the normal aging effect, selection of discriminative voxels, the calculation of the grading biomarker using AD a
the proposed biomarker and demonstrates a significant contribution in accurate prediction of MCI-to-AD conver.
Ultra-wideband raster-scan optoacoustic mesoscopy (RSOM) is a novel modality that has demonstrated unprecedented abil
framework: Deep Learning RSOM Analysis Pipeline (DeepRAP), to analyze and quantify morphological skin features reco
This strategy enabled the automatic recognition of skin layers and subsequent segmentation of dermal microvasculature wit
characterize disease severity and progression well with a strong correlation to physician evaluation and histology. In a uniq
the occlusion and release process, demonstrating accurate performance and reproducibility of DeepRAP. Furthermore, we a
layer have the strongest correlation to age. The ability of our newly developed framework to enable the rapid study of huma

This article proposes a low-complexity data-driven multiuser detector for grant-free nonorthogonal multiple access (GF-NO
grant-access procedure for requesting a transmission slot every time results in significant signaling overhead and latency. In
allocated power level without any grant request. While this significantly reduces the signaling overhead, the access point ha
limit transmissions to be packet-synchronized and add carefully chosen pilots in every packet to facilitate activity detection
detection problem without these constraints, by analyzing the boundaries of the received constellation points in power dom
and better than traditional data-driven detectors for GF-NOMA. Comprehensive simulation results demonstrate the perform

In the realm of recommendation systems, cold start scenarios—where new users or items have insufficient interaction data—
items and drawing parallels between user preferences, the system effectively generates meaningful recommendations despi
experience through personalized suggestions.
Distributed Denial of Service (DDoS) attacks present a severe threat to network security, overwhelming systems with malic
resources and orchestrating defenses across distributed nodes, the framework ensures robust protection against DDoS threa
architecture.

Cloud computing environments often require efficient methods for resource allocation to manage varying demands. This pa
acquisition by evaluating bids for bundles of resources. Utilizing Java and JSP for its implementation, the system provides

Managing energy consumption within consumer-premise systems requires effective scheduling to optimize energy usage an
Java and JSP technologies, the system allows users to efficiently manage their energy consumption through a web-based in

In multi-agent image retrieval systems, processing and ranking images efficiently is crucial for accurate results. This resear
overhead and speeds up the ranking process. Implemented in Java with JSP for its web-based interface, the approach enable

Managing user authorization dynamically in distributed systems requires robust trust models to ensure security and reliabili
web-based interface for administrators to configure and monitor trust metrics. This approach enhances the system's ability t
Effective document summarization relies on understanding the context of words within the text. This study introduces a con
documents to generate coherent and relevant summaries. This approach improves the quality of automated summaries, mak
Scaling elastic applications across multiple cloud environments requires efficient coordination to balance workloads and re
provides a web-based interface for administrators to monitor and adjust scaling operations. By integrating with various clou
Protecting cloud resources from unauthorized access while optimizing costs is a critical challenge. This paper introduces a
for managing firewall rules and monitoring resource usage. The decentralized approach enhances security and allows for dy
Efficiently managing data flows in large-scale cloud data centers requires dynamic scheduling and load balancing. This rese
interface, the approach enables real-time monitoring and adjustment of data flows, improving overall data center performan

This Study explores Detecting and recognizing objects are crucial stepsin interpreting remote sensing images.
At present, deep learning methods are predominantly employed for detecting objectsin remote sensing images,necessitating
small storage in computing devices are hard to afford the large model parameter quantity and high computing
complexity. To address these constraints, this article presents a lightweight detection model called
CSPPartial-YOLO. This model introduces the partial hybrid dilated convolution (PHDC) Block module that combineshybri
information and improvethe detection of small objects with complex distributions in remote sensing images. A backbone an
dataset for object deTection in aerial images (DOTA) dataset.
This study explores ship object detection using Convolutional Neural Networks (CNN), YOLOv5, and YOLOv8, evaluatin

CNNs, known for their robust image processing capabilities, provide a foundational approach but often suffer from longer e

YOLOv5, an advanced real-time object detection model, balances accuracy and speed, offering a streamlined approach with

The latest iteration, YOLOv8, further refines these capabilities, enhancing accuracy and reducing error rates through impro

In our research, we aim to refine the process of identifying the intentions of transfemoral amputees who use powered knee p

This task involves analyzing intricate sensor data to discern the user's movements and actions. To achieve this, we employ
focus on the most relevant information for classification.

This step is crucial for enhancing the accuracy and efficiency of our intent recognition system. Following feature extraction

By optimizing these parameters, we ensure that our classifiers can effectively distinguish between different user intentions

This study focuses on analyzing cancer-associated mutations in the POLB gene using machine learning and bioinformatics

We employ an existing One-Class Support Vector Machine (OCSVM) algorithm to identify potential mutations, leveraging

However, due to OCSVM's limitations in interpretability, we propose using a Decision Tree algorithm. Decision Trees offe

Our methodology includes data collection, preprocessing, and model training, followed by a comparative analysis of the OC

This research aims to enhance the identification of cancer-related mutations in POLB, providing a more interpretable and e

Biometric recognition is an emerging field leveraging physiological and behavioral characteristics for identification and ver

The BIOWISH system utilizes wearable inertial sensors to capture and analyze heart activity, providing a novel approach to

These sophisticated machine learning techniques are adept at handling the nuances of heart activity signals, ensuring accura

The system is designed to predict three distinct states: interruption, no stress, and time pressure. By discerning these states,

This capability is particularly beneficial in environments where continuous monitoring and quick identification are critical,

In recent years, the integration of artificial intelligence (AI) into English as a Foreign Language (EFL) learning and teachin

This study aims to classify these difficulties based on their level of comprehension impact, categorizing them as easy to und

Employing machine learning algorithms such as Random Forest and a hybrid approach combining Logistic Regression and

By analyzing a diverse range of data sources including student performance metrics, language proficiency assessments, and
In the realm of machine learning (ML) education, fostering practical skills and competitive spirit among students is crucial.

This study explores the application of competition-based learning to enhance students' practical and competitive AI abilitie

The research focuses on employing two distinct algorithms, namely random forest regression and lasso regression, to predic

By leveraging these algorithms, the study aims to provide insights into how different ML techniques can be utilized to asse

The findings are expected to contribute to the development of effective educational strategies that not only evaluate academ

Artificial Intelligence (AI) and Machine Learning (ML) have emerged as transformative tools in enhancing glycemic contro

This study focuses on predicting diabetes onset using ML techniques, specifically Random Forest and Logistic Regression,

The objective is to leverage these algorithms to accurately identify early indicators and patterns associated with diabetes, ai

By exploring these methodologies, this research aims to advance the application of AI and ML in diabetes care, highlightin

Opportunities lie in the potential for AI to improve adherence to treatment regimens, enhance patient outcomes through rea

The proliferation of IoT devices in smart cities and various societal applications is accompanied by growing concerns abou
deep learning (DL) for automatic anomaly detection. A hybrid classifier combining BiLSTM and Convolutional Neural Ne
Elephant Herding Optimization (SAEHO), is introduced to fine-tune the model's weights. Experimental results on datasets

The study addresses the challenge of enhancing the performance of Steady-State Visual Evoked Potential (SSVEP) Brain-C

The proposed algorithm integrates Gradient Boosting, Logistic Regression, and Random Forest classifiers within a stacking

Feature extraction is performed using Fast Fourier Transform (FFT), which effectively captures the frequency components
fatigue on classification performance. The combined use of advanced ensemble techniques and adaptive strategies aims to e

Epileptic seizures, characterized by abnormal electrical activity in the brain, present a significant challenge for timely and a

Early and precise detection of seizures is crucial for effective treatment and improving the quality of life for individuals wit

This study proposes an advanced framework for epileptic seizure detection by integrating path signature analysis with a bid

The proposed method leverages the strengths of these techniques to enhance detection accuracy and reliability.

The combination of Bi-LSTM with attention and Random Forest offers a powerful and interpretable model for seizure dete

Parkinson’s disease (PD) is characterized by motor symptoms whose progression is typically assessed using clinical scales,
subtle changes in disease progression and is prone to subjective interpretations. We aimed to develop an automated system
Tapping test, a component of the MDS-UPDRS, from 24 healthy controls and 66 PD patients using ML algorithms for hand
different features according to severity. We compared our video-based disease severity prediction approach against other ap

Learning from unlabeled data or self-learning, can substantially reduce the complexity of machine learning (ML) utilization
restricts its scope of application, especially with nonstationary data distributions in different domains. Leveraging transdom
among interactive objects and learned temporal relations among causal events for identifying and associating labels and inp
proposed method outperforms traditional feature similarity-based semisupervised learning. A computer simulation experim
data distribution.
Ultra-wideband raster-scan optoacoustic mesoscopy (RSOM) is a novel modality that has demonstrated unprecedented abil
framework: Deep Learning RSOM Analysis Pipeline (DeepRAP), to analyze and quantify morphological skin features reco
This strategy enabled the automatic recognition of skin layers and subsequent segmentation of dermal microvasculature wit
characterize disease severity and progression well with a strong correlation to physician evaluation and histology. In a uniq
the occlusion and release process, demonstrating accurate performance and reproducibility of DeepRAP. Furthermore, we a
layer have the strongest correlation to age. The
ability of our newly developed framework to enable the rapid
study of human skin morphology and microvasculature
in-vivo promises to replace biopsy studies, increasing the
translational potential of RSOM

Doing high throughput high accuracy metrology in small geometries is challenging. One approach is to build easily measur
characteristics of devices in the Back End Of Line (BEOL). Given the wide choice of PSR targets, we explore how to selec
trade-off between chip area dedicated to targets and achievable accuracy. We run ML experiments using different selection
be achieved for a reasonable area budget; b) ML model performance across target families varies significantly, thus justifyi
accuracy for a dataset of this size, but relatively small compared to the increase in area budget needed. Ultimately we aim t

Robot-assisted motor training is applied for

neurorehabilitation in stroke patients, using motor imagery
(MI) as a representative paradigm of brain-computer interfaces to offer real-life assistance to individuals facing
movement challenges. However, the effectiveness of training with MI may vary depending on the location of the
stroke lesion, which should be considered. This paper
introduces a multi-task electroencephalogram-based heterogeneous ensemble learning (MEEG-HEL) specifically
designed for cross-subject training. In the proposed framework, common spatial patterns were used for feature
extraction, and the features according to stroke lesions
are shared and selected through sequential forward floating selection. The heterogeneous ensembles were used
as classifiers. Nine patients with chronic ischemic stroke
participated, engaging in MI and motor execution (ME)
paradigms involving finger tapping. The classification criteria for the multi-task were established in two ways,
taking into account the characteristics of stroke patients.
In the cross-subject session, the first involved a direction recognition task for two-handed classification, achieving a
performance of 0.7419 (±0.0811) in MI and 0.7061 (±0.1270)
in ME. The second task focused on motor assessment
for lesion location, resulting in a performance of 0.7457
(±0.1317) in MI and 0.6791 (±0.1253) in ME. Comparing
the specific-subject session, except for ME on the motor
assessment task, performance on both tasks was significantly higher than the cross-subject session. Furthermore,
classification performance was similar to or statistically
higher in cross-subject sessions compared to baseline
models. The proposed MEEG-HEL holds promise in improving the practicality of neurorehabilitation in clinical settings
and facilitating the detection of lesions

In neurodegenerative disorders, neuronal firing patterns and oscillatory activity are remarkably altered in specific brain regi
(PD). In this study, changes in the spike firing patterns and spectral power of local field potentials (LFPs) in the pre-STN (z
arrays (MEAs) with sites distributed at different depths and widths were utilized to record neuronal activities. The spikes in
the cp. Additionally, increased LFP power was observed in the beta bands in the STN. To identify the best performing class
and the fast Fourier transform of the LFPs. The best transfer learning model achieved an accuracy of 95.16%. After fusing t
learning for training models on neural activity. This approach highlights the potential for functional localization within dee
Network slicing is a technique introduced by 3GPP to enable multi-tenant operation in 5G systems. However, the support o
based mechanism enabling defined performance isolation among slices competing for resources. Then, to speed up the reso
architecture. The proposed ML enhancement is evaluated under realistic traffic conditions with respect to the performance c
allocation process ensuring slice performance isolation, efficient resource use, and fairness. Among the considered algorith
algorithms in terms of accuracy (by 20–40 %), sensitiveness to workload variations and training sample size. Finally, ML a
ML framework.

Objective: Despite speech being the primary communication medium, it carries valuable information about a speaker's heal
Previous approaches primarily focused on one particular task, such as differentiating between normal and dysphonic speech

Methods and procedures: This study proposes an approach that combines transfer learning and multitask learning (MTL) to
models and changed their architecture to support multitask learning. Additionally, we conducted binary 'healthy vs. dyspho

Air pollution is a severe environmental problem in urban areas. Accurate air quality prediction can help governments and in
in air quality prediction. However, because of the volatility of air quality and the lack of additional context information, i.e.
training data, heavy computing, and time cost are required. In this paper, we propose a hybrid model to simultaneously pred
indicators from several adjacent monitoring stations; (2) the Empirical Mode Decomposition (EMD) to decompose the air q
public dataset show that our proposed model outperforms the state-of-art air quality forecasting models in both accuracy an

Early prediction of aging trajectories of lithium-ion (Li-ion) batteries is critical for cycle life testing, quality control, and ba
intensive, even in accelerated aging with complex aging mechanisms. This challenge is rooted in the highly complex and ti
incorporated into the model training process to predict the aging trajectory’s knee point (KP). The relationship between the
valuable physical insights to yield accurate KP predictions with small data and weak correlation feature relationship. Based
cycles. In contrast, 100 cells are needed to reach this level of accuracy without the physical insights.

Federated Learning (FL) offers a collaborative training framework, aggregating model parameters from decentralized clien
recognition of established classes due to catastrophic forgetting. This is exacerbated when new clients, unfamiliar to previo
approach. This methodology ensures content-level privacy and significantly alleviates the risk of catastrophic forgetting in
old knowledge to obtain a new global model. We also propose a multi-factor dynamic weighted aggregation strategy that co
more balanced privacy protection for different datasets. Finally, we conducted experiments on CIFAR-100 and ImageNet to

In recent years, advanced magnetic resonance imaging (MRI) methods including as functional magnetic resonance imaging
techniques, such as computer-assisted diagnosis, can benefit from deep learning. With the use of artificial intelligence (AI)
of the most powerful deep learning network such as Convolution Neural network (CNN) and Transfer Learning algorithm f
dimension), the rs-fMRI data can be used to develop diagnostic biomarkers for brain dysfunction. ABIDE is a global collab
typical control (TC) respectively, collected from 17 different sites. Our proposed optimized version of CNN achieved 81.56

Electromyographic (EMG) signals have gained popularity for controlling prostheses and exoskeletons, particularly in the fi
Asian race features, are scarce. Additionally, deep learning algorithms are rarely used for human motion intention recogniti
volume, the JJ dataset, which includes approximately 13,350 clean EMG segments of 10 gait phases from 15 people. This i
Our research explores and compares multiple key issues in this area, including the comparison of sliding time window meth
calf muscles in amputees. Our experiments demonstrate that the adjusted ResNet can achieve significant classification accu
and effective method for lower limb human motion intention pattern recognition.

This study presents a novel method to assess the learning effectiveness using Electroencephalography (EEG)-based deep le
field of brain has shown that innovation ability can be reflected from cognitive ability which can be embodied by EEG sign
signals, a convolutional neural network (CNN)-based Multi-Time Scale Spatiotemporal Compound Model (MTSC) is prop
demonstrate cognitive processes, acknowledging that NeuCube is an excellent method to display the spatiotemporal differe
effectively distinguished. More importantly, new information about navigation is revealed through the analysis of feature v
CircRNA has been proved to play an important role in the diseases diagnosis and treatment. Considering that the wet-lab is
and some methods do not take full advantage of dependencies between attributes. To solve these problems, this paper propo
fuse the circRNA similarity kernels and disease similarity kernels. Then the vectors are connected to make the positive and
the prediction score. The experimental results show that compared with existing methods, KFDAE achieves the best perfor
credible candidate for subsequent wet-lab.

— Graph neural networks (GNN) are increasingly used to classify EEG for tasks such as emotion recognition, motor image
these approaches. We exhaustively search the published literature on this topic and derive several categories for comparison
standard forms of node features, with the most popular being the raw EEG signal and differential entropy. Our results summ
and appropriate modelling of cross-frequency interactions.

Seizure prediction are necessary for epileptic patients. The global spatial interactions among channels, and long-range temp
Many previous deep learning algorithms have achieved some results in automatic seizure prediction. However, most of them
this study, an novel bi-level programming seizure prediction model, B2-ViT Net, is proposed for learning the new generaliz
prediction. In addition, the proposed model can comprehensively learn generalized seizure prediction features in a vast spac
our proposed model has shown promising results in automatic seizure prediction tasks, and provides a certain degree of inte

Electroencephalography (EEG) datasets are characterized by low signal-to-noise signals and unquantifiable noisy labels, wh
reduced generalization performance. In this paper, we propose a novel multi-task collaborative network (MTCN) that integ
representations and establish classification thresholds for targets and non-targets. Two SSL tasks, including the masked tem
learns from multiple tasks to derive a comprehensive representation that captures the essence of all tasks, thus mitigating th
task-shared features, leveraging both label information with SL and feature information with SSL. Experiments conducted o
.

In recent years, there has been a surge in interest regarding the intricate physiological interplay between the brain and the h
appreciation for their bidirectional communication and influence on each other. Our study contributes to this burgeoning fie
during visual emotional elicitation. We extract and transform features from EEG and ECG signals into a 1 Hz format, facili
components in EEG, particularly in the d , ? , and a bands, as essential mediators of information transmission during the co
mediating emotional responses. Additionally, we observe significant arousal-dependent changes in the ? frequency band ac
elicitation, our research enriches the expanding knowledge base in the field of neurophysiology and emotion research.

The ADReSS-M Signal Processing Grand Challenge was held at the 2023 IEEE International Conference on Acoustics, Spe
(AD) and the estimation of cognitive test scoress. Participants were invited to create models for the assessment of cognitive
which predictive models built based on speech in one language generalise to another language. The language data compiled
acoustic features of the speech signal or linguistic characteristics in the context of multilingual AD detection. This paper de
paper concludes with a summary discussion of the ADReSS-M results, and our critical assessment of the future outlook in t

Our Heart Failure Prediction System is intended to assist patients in recognizing their heart state early and receiving treatm
implementing the Logistic Regression algorithm.The framework used in this project is NetBeans. The Front End involves H

This Project aim is to design an uplink Integrated Sensing and Communication (ISAC) in 6G wireless networks, focusing o
spectrum and hardware resources between sensing and communication functions, we propose a joint design strategy. This s
computational complexity and non-convexity. To improve ISAC performance, we first simplify the design by performing s
effective, as confirmed by both theoretical analysis and simulation results. For improving the ISAC performance need to cu
finally calculate the error rate for the transmitting and receiving signals.

Electrocardiography (ECG) is a non-invasive tool for predicting cardiovascular diseases (CVDs). Current ECG-based diagn
deep learning techniques. However, the label scarcity problem, the co-occurrence of multiple CVDs and the poor performan
learning-based models. Addressing them in a unified framework remains a significant challenge. To this end, we propose a
simultaneously with limited supervision. In the ECGMatch, an ECGAugment module is developed for weak and strong EC
Subsequently, a hyperparameter-efficient framework with neighbor agreement modeling and knowledge distillation is desig
problem. Finally, a label correlation alignment module is proposed to capture the co-occurrence information of different CV
Machine Learning (ML), which is occurring in numerous domains that require effective and efficient data classification, is
complexity; nevertheless, they also rely significantly on data, which must be gathered in the data plane. The unavoidable ou
may minimise the interaction between data and control planes while maintaining acceptable monitoring performance is ther
this strategy and suggest P4RTHENON: an architecture that gathers pertinent data in the data plane and mirrors it to the con
P4-native support for runtime data plane pipeline reconfiguration. We used the volumetric DDoS detection use case to test
not deteriorate the overall.

Network service providers have shown a strong interest in using automated network operations that combine software-defin
of the service chaining (SC) problem is to build an acceptable service path from an origin node to a destination node where
as switches and routers. We approached the SC problem as an integer linear programme (ILP) in our earlier work using the
taking into account the trade-off between computational cost and optimality. In this paper, we present a graph neural netwo
the suggested framework outperforms the traditional deep Q-Network based method in achieving almost ideal SC at a faste
demand.

Cricket club management project is designed with the motive of managing a cricket club. This software system consists of
registration and more. This software system assures efficient management and maintains the functioning on a cricket club.
Accurate monitoring and control of T-type three-level inverters (TThLIs) depend on precise phase current measurements. H
(ZPD). To address these issues, we've developed a new method called Asymmetric SVPWM and Error Suppression (APES
technique to identify and correct ZPD errors in current readings
The four-switch buck–boost (FSBB) topology is widely used alongside isolated converters to enhance voltage range capabi
This presentation introduces a novel nonlinear average model and its corresponding linearized small-signal model for the F
with simulation results and are validated through experimental measurements.

Rotating electrical machines greatly suffer from insulation degradation and failure. The adoption of wide bandgap semicon
Discharges (PD) to monitor and diagnose the insulation status and failure. Alternative techniques exploiting the broadband
of cutting-edge broadband frequency techniques aimed to diagnose winding insulation degradation and faults. First, the bro
diagnosis methods are thoroughly reviewed. The analysed methods include the Frequency Response Analysis (FRA) applie
current ringing. Specifc focus is placed on the instrumentation, which often represents the main applicability limitations.

According to experimental data, the suggested inverter may generate cleaner electricity, as evidenced by its ability to attain
in renewable energy applications. MATLAB/Simulink simulations are used to show the dynamic performance and stability
of the multilevel inverters get the rid of more THD in the circuit. Our main objective is to attain the THD rate as 13.58% bu
as input with the solar irradiance and time and use boost converter and DC-DC converter with the controller for regulating
voltages and current from the circuits.

The reduced amount of large synchronous generators results in the need for fast, flexible, and intelligent power distribution
This Project proposes a new approach to control an asynchronous low voltage grid connection, employing a virtual synchro
The grid-forming converter, receiving the primary side frequency measurement, varies the fed grid frequency on the second
This enables the adjustment of the consumed or generated power in the fed grid without the need for additional communica
The performance of the proposed frequency control has been validated through simulation.

The bipolar high voltage DC transmission (HVDC) system that connects offshore wind power plants (WPPs) is redesigned
because WPPs are unable to sustain operations on their own, the shutdown of half of the total WPPs is unavoidable. The W
By disconnecting switches, the suggested reconfiguration method shifts the converters and WPPs from the defective pole to
reconfiguration is developed.
Consequently, even in the event of a dc line failure, the reconfiguration enables the uninterrupted operation of all WPPs. As

Inductive Power Transfer (IPT) technology has emerged as a promising approach for EV charging, offering benefits such a
In this paper, we present the design and development of a 30 kW bidirectional IPT charger with an intermediate coil for EV
The proposed system consists of a primary coil located at the charging station, an intermediate coil, and a secondary coil m
The intermediate coil serves as a coupling element, improving the power transfer efficiency and flexibility of the system.
The bidirectional nature of the charger allows for both charging the EV battery from the grid and discharging the EV batter
Experimental results demonstrate the performance of the 30 kW bidirectional IPT charger, achieving a peak efficiency of o
Solar energy is a sustainable and highly promising renewable energy source. The commonly employed Perturbation and Ob
(MPPT) proves challenging under partial shading conditions (PSCs). This paper proposes a novel MPPT based on segment
array and a boost chopper. The feasibility and effectiveness of the proposed HPO algorithm are validated through a compar
constructed using MATLAB/SIMULINK software. After testing the system in four distinct illumination scenarios, the aver
highest tracking efficiency of 99.99%.

This article proposes a new floating four-phase interleaved chargepump bidirectional dc-dc converter (F4P-ICPBDC) with
enabled by the floating configuration. A reasonably priced asymmetric duty limit control technique is used to guarantee a b
raises the converter's overall efficiency. Additionally, illustrations of the converter's complete operating principles, device s
Lastly, to verify the broad Buck/Boost voltage ratio of the suggested converter between the constant low-voltage side (72 V
Boost mode, respectively. The suggested converter's viability and effectiveness are confirmed by the experimental findings

The disadvantages of the four-leg current source inverter (4L-CSI) are bulkiness and low efficiency. Its advantages include
Buck-4L-CSI) topology are suggested as solutions to these shortcomings. The multilayer properties of 3L-Buck-4L-CSI all
cycles can be easily and directly produced by solving algebraic equations. Furthermore, as compared to traditional modulat
and topology are successful.

This paper proposes a generic and unifed model of the power ?ow (PF) problem for multiterminal hybrid AC/DC networks.
addition to the Slack, PV and PQ nodes, four new node types are introduced to model the DC buses and the buses connectin
different control modes. Compared to other recent works, the proposed method allows multiple ICs to regulate the DC volta
networks under unbalanced conditions and allows for an intentionally negative sequence power injection. In addition to the
of magnitude better than that of other methods presented in the existing recent literature while having the same accuracy

The current-voltage (I-V) characteristic of a photovoltaic (PV) generator is primarily responsible for describing its behavio
defects. An innovative I-V curve tracer for individual PV panels is provided in this research.
It guarantees the ensuing benefits. 1) An improved I-V curve measurement as a result of a creative tracing technique. 2) In-
suggested instrument has been created and constructed. The final prototype has been employed to assess a PV panel's I-V c
This project presents the improvement of voltage stability and control in DC microgrids to enhance voltage stability. A Sim
Optimization (FA-PSO) approach is used to tune Fuzzy Controller to achieve faster convergence, voltage regulation in EV

Supercapacitors (SC) have superior performance for frequency response services in grid-tied photovoltaic (PV) systems ow
However, their variable voltage makes PV/SC hybridization quite challenging.
The current body of literature lacks solutions that offer either a substantial stepup gain for the SC ports when controlled as
when controlled as a current source.
To tackle this concern, this paper proposes a new compact multi-port dc/dc converter that integrates SC at the PV side by m
three additional switches (two switches are soft switched and one is hard switched with low voltage) and three diodes.
This topology allows SC operation at almost their entire voltage range, while a decoupling control method ensures separate
The complete control scheme leverages both the SC and PV array for frequency response and comprises voltage recovery a

This project focuses on the design, simulation, and control of a wind turbine system integrated with a Permanent Magnet Sy
mechanisms, including Maximum Power Point Tracking (MPPT) and pitch angle control. The system includes detailed mo
delivered to the grid, DC link voltage stability, rotor speed regulation, and grid interaction parameters. The project aims to
efficient and sustainable renewable energy solutions.

Accurate prediction of the state-of-charge (SOC) of battery energy storage system (BESS) is critical for its safety and lifesp
model based on gated recurrent unit (GRU), which is specifically designed for complex multi-step SOC prediction in practi
Concurrently, the parameters undergo patching before entering a dual-stage multi-layer GRU, thus enabling the model to ca
extensive validation over multiple days, it is illustrated that the proposed model achieves an absolute error of less than 1.5%

The four-switch buck–boost (FSBB) topology is widely used alongside isolated converters to enhance voltage range capabi
This presentation introduces a novel nonlinear average model and its corresponding linearized small-signal model for the F
with simulation results and are validated through experimental measurements.
Low-frequency oscillations are an inherent phenomena in transmission networks and renewable energy plants should be co
introduce delays of a stochastic nature that degrade the performance of centralised control algorithms. Therefore, controller
oscillation damping that uses a PV plant with all the realistic effects of communication channels taken into consideration. T
oscillation by using the open-loop phase shift compensation. Theoretical developments were validated in a laboratory using
Experimental results show the communication channels impose severe restrictions on the performance of centralised POD c

Hydrogen electrolyzers are promising tools for frequency regulation of future power systems with high penetration of renew
(AELs) and Proton Exchange Membrane Electrolyzers (PEMELs). However, they have trade-offs: dynamic response speed
with reduced costs. A decentralized dynamic power sharing control strategy is proposed where PEMELs respond to the fast
scalability of the system, what is essential for expansion of hydrogen production. The effectiveness of the proposed strategy

This paper proposes decentralized stability conditions for multi-converter systems based on the combination of the small ga
proposed stability conditions are more scalable and computationally lighter, which aim at evaluating the closed-loop system
dynamics and is suitable to analyze large-scale multi-converter power systems that contain grid-following (GFL), grid-form
conservative and can be generally satisfied in practice across the whole frequency range.

Over the past few years, Brazils increasing dependence on electricity has caused a continuous growth in demand and, there
can reduce the reliability of the electrical energy distribution system, therefore requiring detailed study that incorporates sim
readymade templates for protection system equipment such as relays, fuses, and reclosers. Herein, the aim is to model the d
operations divided into fast and slow, the latter one being responsible for permanently opening the section of the system on
performed successfully proved to be a promising proposal for protection studies of power distribution systems.

This paper presents a fast and accurate state-space model for synchronous machines taking into consideration the machine g
stator flux linkages as functions of the state variables, i.e., the winding currents and the rotor position. Different approaches
derivatives so that the loss can be directly interpolated when time-stepping the state-space model. The Simulink implement
for a 150-kVA machine operating under both sinusoidal and pulse-width modulated voltage supplies is presented to validat

Compared to the traditional modular multilevel converter and alternative arm converter, the hybrid multilevel converter (HM
this method has certain limitations, including a restricted range of modulation indices and the inability to support pure react
enables the HMC to achieve a full range of modulation index and four-quadrant operation. Additionally, it demonstrates im
CVB methods, focusing on the SM number, switch number, and SM capacitance. Furthermore, a unified control strategy co
simulation and experimental testing.

In the era of Internet of Things, how to develop a smart sensor system with sustainable power supply, easy deployment and
wearable devices. The contact-to-separate friction nanogenerator (TENG) was prepared by using polychotomy thy lene (PT
2012, Academician Wang Zhong lin and his team invented the triboelectric nanogenerator (TENG), which uses Maxwell di
structure and high instantaneous power density, which provides an important means for building intelligent sensor systems.
large number of electrical signals generated by TENG, and the combination with TENG sensors will promote the rapid dev
capability, and aims to evaluate the feasibility of the sound perception module architecture in ubiquitous sensor networks.

With the development of society, the power system plays an important role in the global energy structure. However, facing
power electronics technology, as one of the research hotspots, integrates IoT and power electronics technology to achieve in
management of power systems using IoT power electronics technology. By analyzing the application of Internet of Things
anomaly detection to promote energy waste reduction and energy saving, and then start from operation and maintenance res
operating costs, and data security. The experimental results show that the operation and maintenance efficiency of the powe
electronics technology reaches 94%. The fault detection accuracy of intelligent monitoring of power equipment based on th
so as to promote the monthly electricity sales revenue of 2.77 million RMB. In addition, the effectiveness of IoT power

This paper proposes an efficient and fast maximum power point tracking (MPPT) algorithm for a wind turbine (WT) conne
and optimal relation methods and is called TS-MPPT. The fuzzy system computes the converter duty cycle using an input t
algorithm resulted in a five-rule TS fuzzy system, which contributed to a fast algorithm in terms of its total execution time
processor-in-the-loop simulation approach show that the TS-MPPT algorithm achieves an effective MPP tracking process w
are demonstrated against others using the proportional-integral controller, the Mamdani fuzzy method, and a TS fuzzy mod
The output power of an ocean wave energy (WE) system has an intermittent and stochastic characteristic. WE output powe
presented in this paper identifies the lowest-cost HESS sizing for WE systems by using a genetic algorithm (GA) optimizat
optimization has been applied in the field of HESS in ocean WE systems and has brought innovation to the literature with i
discharge parameters. The series and parallel connection calculations and the required number of battery and UC cells are g
given as a result of the optimum cost analysis.

Efficiently solving unbalanced three-phase power flow in distribution grids is crucial for accurate grid analysis and simulat
PowerFlowMultiNet, a novel multigraph Graph Neural Network (GNN) framework explicitly designed for unbalanced thre
mechanism with message passing, the framework captures spatial dependencies within the power system network. The data
Multi-Layer Perceptron (MLP) model, each trained and evaluated on the dataset. PowerFlowMultiNet, represented by the G
the robust solution offered by deep learning techniques for modern and future power system applications. This innovative f

Over the past few years, Brazils increasing dependence on electricity has caused a continuous growth in demand and, there
can reduce the reliability of the electrical energy distribution system, therefore requiring detailed study that incorporates sim
readymade templates for protection system equipment such as relays, fuses, and reclosers. Herein, the aim is to model the d
operations divided into fast and slow, the latter one being responsible for permanently opening the section of the system on
performed successfully proved to be a promising proposal for protection studies of power distribution systems.

Multi-agent based small scaled smart grid reinforcement scheme is proposed to manage energy resources by enhancing resi
to grid cost. Interconnected microgrids comprise diverse energy resources that allow sharing energy to balance fluctuation b
customer comfort is compromised. In the second stage, microgrids comprise RER; energy consumption-related charges are
than charges incurred from the grid is defined by 122.1%. The findings show that the average power drawn from utility grid
microgrids generation to reduce the operation cost to 42.64%. Less reliance on the grid, flexible energy use, and avoiding c

We prove that the popular grid-forming control, i.e., dispatchable virtual oscillator control (dVOC), also termed complex d
stability conditions for the transient stability of dVOC in multi-converter grid-connected systems, beyond prior small-signa

In this article, we analytically study the transient stability of grid-connected converters with grid-forming complex droop co
whereas classical droop control does not. We provide quantitative conditions for complex droop control maintaining transie
droop control, we reveal that the unstable trajectories are bounded, manifesting as limit cycle oscillations. Moreover, we ex
dynamics. Our theoretical results contribute an insightful understanding of the transient stability and instability of complex

— In this article, we consider a dc microgrid composed

of distributed generation units (DGUs) trading energy among
each other, where the energy price depends on the total current
generated by all the DGUs. We then use a Cournot aggregative
game to describe the self-interested interaction among the DGUs,
where each DGU aims at minimizing the deviation with respect
to the given reference signals and maximizing the revenue
from the sale of the generated power. Thus, we design a
fully distributed continuous-time equilibrium-seeking algorithm
to compute the generalized Nash equilibrium (GNE) of the
game. We interconnect the designed decision-making algorithm
with the dynamics of the microgrid in a passive way, and,
by leveraging passivity theory, we prove the convergence of the
closed-loop system trajectory to a feasible operating point that
is also a Nash equilibrium of the collective aggregative game.
Finally, we present extensive simulation results that validate the
proposed distributed optimal control scheme, showing excellent
performance.
The intermittency of renewable energy sources (RESs) leads to the incorporation of energy storage systems into microgrids
system is involved in the daily and regulation service markets, characterized by different timescales. The long-term operatio
the electricity market, and minimizes the operational costs. The short-term operations related to the real-time market are ma
and the short-term dynamics and constraints of the equipment. In addition, the LLC is in charge of smoothing the power pro
compared to other strategies, the controller yields fewer state switches in the hydrogen devices, thus extending their lifespa

Efficiently solving unbalanced three-phase power flow in distribution grids is pivotal for grid analysis and simulation. Ther
especially Graph Neural Networks (GNNs), have emerged. However, existing literature primarily focuses on balanced netw
three-phase power grids. The proposed approach models each phase separately in a multigraph representation, effectively c
PowerFlowMultiNet outperforms traditional methods and other deep learning approaches in terms of accuracy and computa

The prevailing methodology in data-driven fault detection leverages synthetic data for training neural networks. However, i
range of real-world data, we introduce FaultSSL, a semi-supervised fault detection framework. This method is based on the
incorporate vast unlabeled field data into the training process. The two proxy tasks are PaNning Consistency (PNC) and Pa
to the global seismic volume. PTC emphasizes the spatially consistent nature of faults. It ensures that the predictions for the
objectives, they uniformly contribute to the enhancement of performance. Experiments showcase the exceptional performan
promising route for incorporating copious amounts of field data into training and fostering model generalization across a br

Optimal power flow (OPF) is a fundamental tool for the operation analysis of bipolar DC distribution network (DCDN). Ho
voltage and current. This paper addresses this issue by establishing a convex OPF model that can be used for the planning a
and convenience in power optimization problems. Furthermore, the original OPF model based on power injection-based eq
feasible region of the convex model, thereby reducing the influence of SOCP relaxation. To enhance the tightness of the fea
the efficacy of the boundaries associated with the second-order cone constraints. The effectiveness of the proposed OPF mo
optimization of the bipolar DCDN. Compared to employing the SOCP relaxation method alone, the relaxation gap is reduce

Efficiently solving unbalanced three-phase power flow in distribution grids is pivotal for grid analysis and simulation. Ther
especially Graph Neural Networks (GNNs), have emerged. However, existing literature primarily focuses on balanced netw
three-phase power grids. The proposed approach models each phase separately in a multigraph representation, effectively c
PowerFlowMultiNet outperforms traditional methods and other deep learning approaches in terms of accuracy and computa

Emotion recognition using EEG signals has gained significant attention in recent years due to its potential applications in v
challenges. In this study, we propose an Attention-Based Hybrid Deep Learning Model for EEG Emotion Recognition, whi
promising results in recognizing emotions from EEG data, paving the way for enhanced human-machine interaction and em

Emotion recognition from EEG (electroencephalography) signals is a challenging yet promising area of research, with appl

Traditional approaches, such as those using Random Forest algorithms, have shown potential but often fall short in effectiv

In this study, we propose a novel framework employing Multi-Scale Masked Autoencoders (MSMAE) combined with Con

Utilizing the Seed IV EEG dataset, our method leverages the multi-scale feature extraction capabilities of MSMAE to hand

Sleep stage classification is pivotal in understanding sleep disorders and improving overall sleep quality. Traditional approa
stages of sleep.

This study proposes a novel multi-modal sleep stage classification framework utilizing Multi-Scale Masked Autoencoders (

The system integrates multi-modal data sources, specifically EEG, EOG, and EMG signals, to leverage complementary info

The framework employs a two-stream encoder-decoder architecture designed to process and fuse these diverse data modali
Role of AI in Regulating Timetable Scheduling using a Python web app built with Streamlit involves leveraging artificial in
requirements, such as resource availability, user preferences, and scheduling conflicts, to generate optimal timetables. Strea
learn and TensorFlow, are employed to build models that predict and resolve scheduling conflicts, optimize resource alloca
data and feedback. By integrating these AI-driven insights into the scheduling process, the application enhances efficiency,

In today’s fast-paced world, the complexity of human emotions often leaves individuals feeling like a ship navigating turbu
algorithms and deep learning techniques that continuously learns from daily interactions and biometric data, discern pattern
patterns, or seasonal changes. The power of Natural Language Processing (NLP) propels AI systems to analyze the sentime
comprehensive emotional portfolio, illuminating with alarming clarity when those evocative swings arise. Combine this wi
health. The AI engine detects when your heart races in excitement or sinks during stress, correlating physiological changes
shows a downward trend, or recommend mindfulness exercises when patterns of anxiety arise. Want a little creativity boost
health professionals can use these insights to tailor their approaches and monitor patient progress over time, thereby transfo
protection. How do we maintain the human touch in detecting emotions when we rely so heavily on algorithms? The synerg
emotional intelligence. This technology can not only assist in recognizing when we’re poised at the edge between joy and d
darkest corners of our psyche while highlighting the beautiful intricacies of our human experience.

End-to-End Encryption in Financial Documents Using Voice Command is a cutting-edge Streamlit web application that com
implementing end-to-end encryption for all financial documents, safeguarding them from unauthorized access and tamperin
Streamlit framework provides a streamlined and responsive interface, allowing users to seamlessly upload, encrypt, and ma
integrating voice commands with end-to-end encryption, the application offers a user-friendly, efficient, and highly secure

IPL Score Prediction using a Flask app is an innovative web application designed to forecast scores for Indian Premier Leag
player statistics, and current game conditions. The Flask framework serves as the backbone of the application, offering a lig
analyze patterns and make accurate score forecasts. These models utilize algorithms such as regression analysis, ensemble m
such as team line-ups and pitch conditions, to receive predictive insights. The system also provides visualizations of predic
offers cricket enthusiasts and analysts a valuable tool for anticipating match results and making informed decisions.

On-Road Vehicle Breakdown Assistance Finder using Python is a practical web application designed to help drivers quickl
roadside help. The application features a user-friendly interface where drivers can input their location details, vehicle inform
companies or roadside assistance teams. Using frameworks like Flask or Django for backend management, the app process
such as automated notifications to the nearest service provider, estimated arrival times, and live tracking of assistance vehic
critical situations.

In today's fast-paced financial markets, the integration of Artificial Intelligence (AI) into stock price management systems h
machine learning algorithms and predictive analytics to forecast market trends, optimize trading strategies, and enhance dec
precision and confidence. Its ability to adapt to changing market
conditions and identify emerging patterns offers a significant advantage over traditional methods. The system employs soph
language processing, neural networks, and sentiment analysis to refine its predictions and recommendations. These technol
not only numerical data but also qualitative factors such as news sentiment and geopolitical events. As a result, users benef
dynamics, allowing for more informed investment decisions and efficient portfolio management. Ultimately, this AI-assiste
returns, minimize risks, and support strategic financial planning in an increasingly complex and competitive environment.

Price Negotiator Ecommerce ChatBot System using Streamlit is an innovative web application designed to enhance the onl
negotiate prices on various products. The chatbot, integrated into the Streamlit app, leverages natural language processing (
personalized discount suggestions based on user input and predefined rules. Streamlit’s intuitive interface allows for seamle
user preferences, and providing insights into price trends. By automating the negotiation process, the Price Negotiator Chat
Orthogonal Time Frequency Space (OTFS) modulation has established itself as a dependable protocol for high-speed vehic
orthogonal frequency division multiplexing (OFDM), OTFS demonstrates superior performance enhancements in scenarios
with the established OFDM waveform highlights the potential of OTFS for achieving notably lower bit error rate (BER) un
scale integration (VLSI) architecture for the OTFS transmitter and the receiver by using the LU decomposition technique fo
timing analysis, and functionality testing of the proposed architecture

The goal of this work is to speed up server-side cryptographic pairing procedures on field-programmable gate arrays (FPGA
side applications, where the main goal is maximum performance after FPGA resources are depleted, these topologies are pr
Their low operation frequency and low digital signal processor (DSP) utilisation make their architectures inefficient. In this
method. When compared, the algorithm displays the maximum throughput and effiency efficiency. Secondly, we create a p
BN254 and BLS12_381 pairs on the suggested processor architecture indicate that it achieves good throughput, which is ro

Orthogonal time frequency space (OTFS) modulation has established itself as a dependable protocol for high-speed vehicul
division multiplexing (OFDM), OTFS demonstrates superior performance enhancements in scenarios involving rapidly mo
OFDM waveform highlights the potential of OTFS for achieving a notably lower bit error rate (BER) under various conditi
OTFS transmitter and the receiver by using the lower–upper (LU) decomposition technique for the first time in the literatur
number of lookup tables (LUTs) and 79.984% less in the number of flip-flops (FFs), which shows that our design is more o
receiver architecture for the first time in the literature, followed by timing analysis and functionality testing of the proposed

Monitoring of biomedical data, such as electrocardiogram (ECG) signals, requires accelerators, which can process data stre
asymptomatic and critical health conditions, such as atrial fibrillation (AF). Such continuous data streams pose unique cons
constraints to define common operating conditions, which guide the design of ECG accelerators in an algorithm–hardware
classifier, as well as the ECG accelerator executing the classifier in a continuous manner. As an example, the constraints ar
to estimate costs for the hardware design. In the end, it is essential for future ECG accelerators to adhere to common constr
The extended greatest common divisor (XGCD)
computation is a critical component in various cryptographic
applications and algorithms, including both pre- and postquantum cryptosystems. In addition to computing the greatest
common divisor (GCD) of two integers, the XGCD also produces
Bézout coefficients ba and bb which satisfy GCD(a, b) = a× ba +
b × bb. In particular, computing the XGCD for large integers
is of significant interest. Most recently, XGCD computation
between 6479-bit integers is required for solving Nth-degree
truncated polynomial ring unit (NTRU) trapdoors in FALCON,
a National Institute of Standards and Technology (NIST)-selected
postquantum digital signature scheme. To this point, existing
literature has primarily focused on exploring software-based
implementations for XGCD. The few existing high-performance
hardware architectures require significant hardware resources
and may not be desirable for practical usage, and the lightweight
architectures suffer from poor performance. To fill the research
gap, this work proposes a novel FPGA-based scalable and
lightweight accelerator for large integer XGCD (FELIX). First,
a new algorithm suitable for scalable and lightweight computation of XGCD is proposed. Next, a hardware accelerator (FE
is presented, including both constant- and variable-time versions.
Finally, a thorough evaluation is carried out to showcase the
efficiency of the proposed FELIX. In certain configurations,
FELIX involves 81% less equivalent area-time product (eATP)
than the state-of-the-art design for 1024-bit integers, and achieves
a 95% reduction in latency over the software for 6479-bit integers
(FALCON parameter set) with reasonable resource usage. Overall,
the proposed FELIX is highly efficient, scalable, lightweight, and
suitable for very large integer computation, making it the first
such XGCD accelerator in the literature (to the best of our
knowledge)

Dynamic Task Scheduling is an enticing programming model aiming to ease the development of parallel programs with int
schedule work to available cores. Traditional SW-only systems implicate scheduling overheads of around 30K processor cy
systems might support high performance scheduling on processors with up to eight cores, but questions remained regarding
capable, 30-core RISC-V system with hardware accelerated Task Scheduling. We use this implementation to show that HW
than previous solutions. Finally, we outline ways in which this architecture could be augmented to overcome inter-core com

Biopotential acquisition chopper instrumentation amplifiers require a dc-servo loop (DSL) in order to filter electrode dc off
depth noise analysis of biopotential acquisition chopper instrumentation amplifiers with analog DSLs. Analytical expressio
circuits targeting biopotential recording systems. These circuits are implemented using a standard 180 nm CMOS technolog
performance, and design strategies for noise optimization.
—As the benefits of Moore’s Law diminish, computing performance and efficiency gains
are increasingly achieved through specializing hardware to a domain of computation. However
this limits the hardware’s generality and flexibility. Field Programmable Gate Arrays (FPGAs),
microchips which can be re-programmed to implement arbitrary digital circuits, enable the
benefits of specialization while remaining flexible. A challenge to using FPGAs is the complex
computer aided design flow required to efficiently map a computation onto an FPGA.
Traditionally these design flows are closed-source and highly specialized to a particular vendor’s
devices. We propose an alternate data-driven approach which uses highly adaptable and
re-targettable open-source tools to target both commercial and research FPGA architectures.
While challenges remain, we believe this approach makes the development of novel and
commercial FPGA architectures faster and more accessible. Furthermore, it provides a path
forward for industry, academia, and the open-source community to collaborate and combine
their resources to advance FPGA technology.

The security of cloud field-programmable gate arrays (FPGAs) faces challenges from untrusted users attempting fault and s
amplified in multi-tenancy scenarios. Detecting such threats before loading onto the FPGA is crucial, but existing methods
We present MaliGNNoma, a machine learning-based solution that accurately identifies malicious FPGA configurations. Se
representation of FPGA netlists, MaliGNNoma employs a graph neural network (GNN) to learn distinctive malicious featur
responsible for the malicious classification.
Through extensive experimentation on the ZCU102 board with a Xilinx UltraScale+ FPGA, we validate the effectiveness o
classification accuracy and precision of 98.24% and 97.88%, respectively, surpassing state-of-the-art. We compare MaliGN
Additionally, we make MaliGNNoma and its associated dataset publicly available.

The posit™ format was introduced in 2017 as an alternative to replacing the widespread IEEE 754. Posit arithmetic provide
as competitive as the IEEE 754 ones yet. The HUB approach was presented in 2016 to reduce the hardware cost of floating
product for adders and multipliers, respectively, while maintaining a similar level of accuracy. In addition, synthesis results

Transport triggered architectures (TTAs) follow the static programming model of very long instruction word (VLIW) proce
architectures add flexiblity via their ability to switch instruction sets during execution. The added flexibility is interesting fo
exploitation of instruction level parallelism. In this article, we introduce a dual instruction-set architecture, “Dual-IS”, that
a compilation method that is able to independently target code for both instruction sets based on static code analysis and a m
which resulted in a total energy consumption reduction of 26% and a 0.4% lower run time.

Safeguarding your wireless messages! This research proposes a method to achieve this using a special surface called STAR
towards the receiver, considering how the STAR-RIS will bounce it back. MMSE ensures the signal reaches the receiver cl
STAR-RIS element into strength (amplitude) and direction (phase). Then, it uses a special MM technique to find the optima

Innovations in machine learning (ML) and deep learning (DL) have enabled network intrusion detection systems (NIDS) to
based NIDS. While packet-based NIDS can analyse data and identify attacks in real-time, flow-based NIDS are best suited
positives and negatives are produced. Furthermore, the majority of packet-based NIDS that have been suggested in the liter
To overcome these restrictions we suggest a brand-new methodological framework for packet-based NIDS that takes into a
using our system. After that, it creates an intrusion detection model using convolutional neural networks to analyse these ph
examples through tests utilizing publically available huge datasets.

Interleaved training is a promising technique for reducing training overhead in massive MIMO systems. This project invest
to optimize training efficiency in correlated channel environments. Analytical expressions for average training length are de
conventional methods.

Spiking neural networks (SNNs) are particularly appealing for edge intelligence applications where resources are scarce be
edge nodes, each of which has a subset of spiking neurons. We define the problem of minimising the energy consumption o
computing and wireless communications. In particular, a simplified homogeneous SNN is investigated initially, and it is sh
By using the spike statistics, the techniques are further extended to heterogeneous SNNs. Comprehensive simulation outcom
This project simulates a MIMO-OFDM communication system leveraging 16-QAM modulation to assess its performance a
MIMO channel with cyclic prefix to handle inter-symbol interference. At the receiver, the system uses FFT for signal proce
(SNR), Packet Error Rate (PER), throughput, Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean A
performance in practical scenarios. Additionally, the impact of various optimization algorithms on system performance is e
improvements in MIMO-OFDM systems for real-world applications.

In recent years, a new technology called Simultaneously Transmitting and Reflecting Reconfigurable Intelligent Surface (S
networks. Our research introduces an advanced version of this technology called Active STAR-RIS (ASTARS), which is pa
Signal Quality this focus on enhancing the signal-to-noise ratio (SNR), which means we want to make the good signals mu
communication (like sending messages) and sensing (like detecting the distance and speed of objects). Using OFDM: We u
in challenging conditions.

Deterministic routing has emerged as a promising technology for future non-terrestrial networks (NTNs), offering the poten
These challenges encompass the intricacy of jointly scheduling transmission links and cycles, as well as the difficulty of ma
expanded graph (TEG) to represent the heterogeneous resources of an NTN in a time-slotted manner. With TEG, we meticu
(ILP), providing a robust yet time-consuming performance upper bound. To address the considered problem with reduced c
Consequently, we propose a polynomial-time complexity algorithm, enabling the dynamic selection of optimal transmissio
compared to existing routing strategies.

A simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) assisted simultaneous wireless
multiple single-antenna information users (IUs) and energy users (EUs), where two practical STAR-RIS operating protocol
that simultaneously maximizes the minimum data rate and minimum harvested power, is employed to investigate the funda
via the ? -constraint method, which is then reformulated by approximating semi-infinite inequality constraints with the S-pr
in STAR-RIS beamforming design. Furthermore, the developed algorithm is extended to optimize the time allocation policy
especially in terms of harvested power for EUs; 2) the ES protocol obtains a better user fairness performance when focusing
design to attenuate these effects.

Radio frequency (RF) wireless power transfer (WPT) is a promising technology for sustainable support of massive Internet
considers a multi-antenna RF-WPT system with multiple non-linear energy harvesting (EH) nodes with energy demands ch
requirements. We model the problem as a Markov decision process and propose a solution relying on a low-complexity bea
DDPG-based approach converges with the number of episodes and reduces the system's power consumption, while the outa

Intelligent Reflecting Surface (IRS) is a communication technology that can control the phase shift and reflection of the inc
modeling. Communication assisted by the IRS takes the form of a mixture channel, composed of a direct link and cascaded
network environment. These limitations motivate the development of a tractable and highly accurate channel model for IRS
distributions to model IRS-assisted communication and derive distributions of the mixture channel for both multiplicability
validated through extensive numerical simulation. These results indicate that the mixture Gamma distribution-based approx

Deep learning-based physical-layer secret key generation (PKG) has been used to overcome the imperfect uplink/downlink
specific environment where the training samples and test samples follow the same distribution, which is unrealistic for real-
to generate keys quickly and efficiently in multiple new environments. Specifically, we propose deep transfer learning (DT
quickly adapt and deploy the model to new environments. Simulation and experimental results show that compared with th
algorithm can achieve better performance than the DTL algorithm with less cost.

The spiking neural network (SNN) is distinguished by its ultra-low power consumption, making it attractive for resource-lim
information through wireless channels. To leverage the benefits of the joint design of neuromorphic computing and wireles
probability. Particularly, a simplified homogeneous SNN is first explored, where the system is proved to have stationary sta
to heterogeneous SNNs by exploiting the statistics of spikes. Extensive simulation results on neuromorphic datasets demon
state-of-the-art recurrent neural networks (RNNs) but are much more bandwidth-efficient and energy-saving.

In unmanned space exploration, the cooperation among space robots requires advanced communication techniques. In this p
daughter probes are distributed across the planetary surface. During each control cycle, the mother spacecraft senses the env
indivisibility of the SC 3 loop, we optimize the mother-daughter downlink for closed-loop control. The optimization object
optimal block length and then transform the power allocation problem into a tractable convex problem. We further derive th
power allocation principles. In particular, for time-insensitive control tasks, we find that the proposed scheme demonstrates
In this paper, we present an iterative algorithm
that detects and estimates the specular components (SCs) and
estimates the dense component (DC) of single-input—multipleoutput (SIMO) ultra-wide-band (UWB) multipath channels.
Specifically, the algorithm super-resolves the SCs in the delay–
angle-of-arrival domain and estimates the parameters of a
parametric model of the delay-angle power spectrum characterizing the DC. Channel noise is also estimated. In essence,
the algorithm solves the problem of estimating spectral lines
(the SCs) in colored noise (generated by the DC and channel
noise). Its design is inspired by the sparse Bayesian learning
(SBL) framework. As a result the iteration process contains a
threshold condition that determines whether a candidate SC shall
be retained or pruned. By relying on results from extreme-value
analysis the threshold of this condition is suitably adapted to
ensure a prescribed probability of detecting spurious SCs. Studies
using synthetic and real channel measurement data demonstrate
the virtues of the algorithm: it is able to still detect and accurately
estimate SCs, even when their separation in delay and angle
is down to half the Rayleigh resolution limit (RRL) of the
equipment; it is robust in the sense that it tends to return
no more SCs than the actual ones. Finally, the algorithm is
demonstrated to outperform a state-of-the-art super-resolution
channel estimator in terms of robustness in the estimation of
the amplitudes of specular components closely spaced in the
dispersion domain.

A frequency-switch strategy is introduced into the magnetic induction-based wireless underground sensor network (MI-WU
discussion about the high-reliability routing design of MI-WUSN. First, we analyze the frequency-selective property and m
in dynamic MI-WUSN as a constrained optimization problem. Finally, we evaluate how various design parameters of our o

Progressing towards a new era of Artificial Intelligence (AI) -enabled wireless networks, concerns regarding the environme
made in FL, its environmental impact is still an open problem. Targeting the minimization of the overall energy consumptio
performance of the model. To this end, we propose a Soft Actor Critic Deep Reinforcement Learning (DRL) solution, wher
synchronization method, along with a computationally cost effective FL environment are proposed, with the goal of further
solutions on different network environments and FL architectures, achieving a decrease of up to 94% in the total energy con

Semantic status update communication (SSUC) is envisioned to provide content-aware and energy efficient information de
incorporating the knowledge base (KB)-enabled semantic network into a discrete time Markov chain, we investigate the SU
local KB to keep semantic match with the transmitter and infer or recover the semantic information from received status up
prove that the joint transmission and updating scheduling policy has optimal threshold structure with respect to SUL. Simul
framework over the traditional non-semantic status update system in terms of improving the timeliness and reducing the en

A novel hybrid active-passive reconfigurable intelligent surface (RIS) transmitter enabled downlink multi-user communica
multiple users. The system energy efficiency (EE) maximization problem is formulated by jointly optimizing the RIS eleme
Using the Dinkelbach relaxation, the original mixed-integer nonlinear programming problem is transformed into a nonfract
operating mode for each RIS element. Then, the RIS beamforming and power allocation coefficients are properly designed
exploiting the Big-M formulation technique. Numerical results validate that: 1) The proposed hybrid RIS scheme yields hig
performance, especially the latter can achieve precise design of RIS elements with low complexity; and 3) For a fixed-size
Integrated sensing and communication (ISAC) technology is at the forefront of next-generation communication, enhancing
challenge. While it opens up new avenues for application, it also raises significant concerns regarding the privacy of sensiti
that contribute to privacy and security vulnerabilities. It also identifies the technical obstacles that stand in the way of achie
mitigate these potential threats and tackle the technical challenges through a secure framework for information handling an
coordinate defense mechanisms, including deploying friendly jammers to thwart malicious devices and utilizing reconfigur
SPPN framework, which not only strengthens the network's defenses but also significantly improves its sensing and commu

Federated learning has been rapidly evolving and gaining popularity in recent years due to its privacy-preserving features, a
model performance and user and data privacy. For this reason, one of the main motivations for decentralized federated learn
challenging the system with new privacy threats. Thus, performing a thorough security analysis in this new paradigm is nec
decentralized federated learning are also considered in this study.

In this paper, we investigate the effect of signal delay in communicated information in connected and autonomous vehicles
control law for each vehicle in the platoon by considering two cases: cooperative adaptive cruise control (CACC) strategy w
headway is affected by signal transmission delay due to wireless communication. We provide a systematic approach to the
string stability of the platoon under the presence of signal delay. We corroborate the main result with numerical simulations

High data rate and low-latency vehicle-to-vehicle (V2V) communication are essential for future intelligent transport system
scenarios and datasets. This is important at the high-frequency bands where more spectrum is available, yet harvesting this
mmWave vehicle-to-vehicle communications. It presents a two-vehicle testbed that comprises data from a 360-degree came
up to 100 km per hour. More than one million objects were detected across all images, from trucks to bicycles. This work f

Authenticated group key agreement (AGKA) protocols protect the security of communications among a group of users. Du
computational Diffie-Hellman problem. The proposed AGKA protocol achieves sound dynamicity and efficiency. With 10
network (VANET). SC-AGKA, a self-certified authentication and key agreement protocol for VANET is presented. Pseudo
and efficiency.

This paper presents an optimization approach for cooperative Medium Access Control (MAC) techniques in Vehic-ular Ad
Access with Collision Avoidance (CSMA/CA) protocol, featuring selective RSU probing and adaptive transmission. It utili
propose the RSU Probing and Cooperative Access (RPCA) strategy, a two-stage approach based on dynamic inter-vehicle d
implementation in VANETs, we develop a distributed MAC algorithm with periodic location updates. It adjusts thresholds
results confirm the effectiveness and efficiency of our algorithm.

Open radio access networks (RAN) enhance the capabilities of traditional RAN by introducing features such as interoperab
between vehicles and RAN intelligence controller (RIC). However, efficient data sharing between vehicles and RIC suffers
smart environments to improve the performance of wireless communication systems. In the proposed research, our main fo
multi-hop passive beamforming over pairwise line-of-sight links. To maximize the overall network sum-rate, we propose an
means clustering to group the IRSs according to their location. In the next stage, for each group, we select the best IRS-assi
outperforms existing IRS selection techniques in multiple IRS-enabled multi-hop communication systems.

Joint communication and sensing allows to share frequency spectrum, hardware, and signal processing blocks between com
future standardized technologies for connected vehicles can be used to detect targets nearby without overloading the alread
sensing purposes; specifically, we evaluate the impact of physical and radio access communication parameters on the sensin
resource allocation policies, have a non-negligible impact on the communication and sensing performance. In particular, it
packet size is different compared to the inference free case.

Cooperatively utilizing both ego-vehicle and infrastructure sensor data via V2X communication has emerged as a promisin
performance, resulting in underutilized data potential. In this paper, we introduce UniV2X, a pioneering cooperative autono
for effective vehicle-infrastructure cooperation, offering three advantages: 1) Effective for simultaneously enhancing agent
fusion with interpretability of this hybrid data. We implement UniV2X, as well as reproducing several benchmark methods
as all intermediate output performance.
V2X cooperation, through the integration of sensor data from both vehicles and infrastructure, is considered a pivotal appro
accuracy through end-to-end learning, leading to insufficient attention to the safety issues of autonomous driving. To addre
framework employs a deformable attention-based data fusion strategy, effectively facilitating cooperation between vehicles
ensuring high reliability in the data fusion process; 3) superior end-to-end perception compared to modular approaches. Fur

Accurate bearing load monitoring is essential for their Prognostics and Health Management (PHM), enabling damage asses
introduced sensor rollers enable direct bearing load monitoring but are constrained by their battery life. Data-driven virtual
distribution (e.g., correlating temperature with load), traditional machine learning algorithms struggle to fully exploit these
sensor signals, mapping existing measurements (temperature, vibration) to bearing loads. Since temperature and vibration s
load prediction. Our results demonstrate that HTGNN outperforms Convolutional Neural Networks (CNNs), which struggle

This paper addresses the joint design of the transmit parameters (i.e., radar code/frequency increments) and the receive filte
transmitted waveforms and the antenna array features, along with conventional thermal noise. The chosen optimization poli
this context, a bespoke Minorization-Maximization (MM)-Maximum Block Improvement (MBI) algorithm is proposed to t
computational complexity for its implementation. Finally, numerical results are provided to show the effectiveness of the n

Benefitting from the vast spatial degrees of freedom, the amalgamation of integrated sensing and communication (ISAC) an
deployed in massive MIMO-ISAC raises critical challenges in acquiring both accurate channel state information and target
addresses both the channel estimation and target sensing problems. Specifically, by parameterizing the high-dimensional co
dimensions. Then, we propose a shared training pattern adopting the same time-frequency resources such that both the chan
uniqueness condition of the tensor factorization and the maximum number of resolvable targets by utilizing the specific Va
targets/channels. In addition, we propose a segment-based shared training pattern to facilitate the channel and target parame
accuracy, sensing resolution, and training overhead reduction.

Active reconfigurable intelligent surface (ARIS) is a promising way to compensate for multiplicative fading attenuation by
fading channels. The effects of hardware impairments (HIS) and reflection coefficients on ARIS-NOMA networks with imp
of outage probability and ergodic data rate with ipSIC/pSIC for ARIS-NOMA-HIS networks. According to the approximate
delay-limited and delay-tolerant transmission schemes. The simulation findings are presented to demonstrate that: i) The ou
OMA; ii) As the reflection coefficient of ARIS increases, ARIS-NOMA-HIS networks have the ability to provide the streng

This article investigates covert communication in simultaneously transmitting and reflecting reconfigurable intelligent surfa
the covertness performance of the considered system, we first derive closed-form expressions for the detection error probab
maximize the effective covert rate (ECR) is proposed. Simulation results verify that the maximum ECR of the considered s

The upcoming sixth generation (6G) driven Internetof- Things (IoT) will face the great challenges of extremely low power
(RCom) assisted non-orthogonal multiple access (NOMA) network, which simultaneously enables traditional relay network
characterize the outage performance of the proposed system in the non-asymptotic SNR region. We derive the outage proba
perfect agreement, we discover that in the high SNR regime, the OP for ABCom tends to be a constant, leading to a zero di
reliability of the system under the ideal condition is significantly improved; Moreover, in the lower multiplexing gain regim
performance metrics by adapting the reflection parameter.

An intelligent omni-surface (IOS) assisted holographic multiple-input and multiple-output architecture is conceived for 360
approximation method, while considering the signal distortion at transceivers imposed by hardware impairments (HWIs). F
simulation results show that the achievable rate of the NOMA scheme is higher than that of its orthogonal multiple access c
This paper proposes a scalable framework to analyze the throughput of the grant-free power-domain nonorthogonal multipl
reflects packet errors caused by power collisions, characterized by GF-NOMA, based on the power level design guaranteein
models. Also, this key idea enables optimizing the per-level offered load rather than a uniform one in typical optimization p
future access control methods in GF-NOMA. First, our analytical model achieves an approximation error of only 0.4% for t
optimal per-level offered load restrictively improves the throughput above the optimally uniform per-level offered load. Fin
uniform per-level offered load.
 Project ID Title

IACC: Cross-Illumination Awareness and Color Correction for Underwater

2024-25_IMG_001
Images Under Mixed Natural and Artificial Lighting

2024-25_IMG_002 Multiple Latent Space Mapping for Compressed Dark Image Enhancement

TRTAR: Transmissive RIS-assisted Through-the-wall Human Activity

2024-25_IMG_003
Recognition

2024-25_IMG_004 ChatCAD+: Towards a Universal and Reliable Interactive CAD using LLMs

Federated-Reinforcement Learning-Assisted IoT Consumers System for

2024-25_IMG_005
Kidney Disease Images

A Colorectal Coordinate-Driven Method for Colorectum and Colorectal

2024-25_IMG_006
Cancer Segmentation in Conventional CT Scans

Anomaly Detection for Medical Images Using Teacher–Student Model With

2024-25_IMG_007
Skip Connectionsm Mingxuan Liu and Multiscale Anomaly Consistency

Multi-Task Learning for Fatigue Detection and Face Recognition ofDrivers

2024-25_IMG_008
via Tree-Style Space- Channel Attention Fusion Network

Direction-Oriented Visual-semantic EmbeddingModel for Remote Sensing

2024-25_IMG_009
Image-text Retrieval

Development of Convolutional Neural Network to Segment Ultrasound

2024-25_IMG_010
Images of Histotripsy Ablation

Recurrent Generic Contour-based Instance Segmentation with Progressive

2024-25_IMG_011
Learning

Ultrasound Nodule Segmentation Using Asymmetric Learning with Simple

2024-25_IMG_012
Clinical Annotation

Joint Learning of Blind Super-Resolution and Crack Segmentation for

2024-25_IMG_013
Realistic Degraded Images

Project ID Title

2024-25_IMG_014 Light-weight Retinal Layer Segmentation with Global Reasoning

2024-25_IMG_015 BoNuS: Boundary Mining for Nuclei Segmentation with Partial Point Labels

CM-MaskSD: Cross-Modality Masked\ Self-Distillation for Referring Image

2024-25_IMG_016
Segmentation

From Canteen Food to Daily Meals: Generalizing Food Recognition to More

2024-25_IMG_017
Practical Scenarios
 Harvard Glaucoma Fairness: A Retinal Nerve Disease Dataset for Fairness
2024-25_IMG_018
Learning and Fair Identity Normalization

A Review of Building Extraction From Remote Sensing Imagery:

2024-25_IMG_019
Geometrical Structures and Semantic Attributes

Enhancing Contrastive Learning With Positive Pair Mining for Few-Shot

2024-25_IMG_020
Hyperspectral Image Classification

Enhanced Biometric Template Protection Schemes for Securing Face

2024-25_IMG_021
Recognition in IoT Environment

Mean-Weighted Collaborative Representation-Based Spatial-Spectral Joint

2024-25_IMG_022
Classification for Hyperspectral Images

Lossless Data Hiding in NTRU Cryptosystem by Polynomial Encoding and

2024-25_IMG_023
Modulation

An Interpretable and Accurate Deep-Learning Diagnosis Framework Modeled

2024-25_IMG_024
With Fully and Semi-Supervised Reciprocal Learning

2024-25_IMG_025 High-Frequency Space Diffusion Model for Accelerated MRI

A Test Statistic Estimation-Based Approach for Establishing Self-

2024-25_IMG_026
Interpretable CNN-Based Binary Classifiers

Project ID Title

Multi-view learning for automatic classification of multi-wavelength auroral

2024-25_IMG_027
images

Time Efficient Ultrasound Localization Microscopy Based on A Novel Radial

2024-25_IMG_028
Basis Function 2D Interpolation

DiffWater: Underwater Image Enhancement Based on Conditional Denoising

2024-25_IMG_029
Diffusion Probabilistic Model

Guided Filter of Random Patches Network and Relaxed-Collaborative-

2024-25_IMG_030
Representation-Based Hyperspectral Image Classification

Active Learning-Based Spectral–Spatial Classification for Discriminating

2024-25_IMG_031
Tree Species in Hyperspectral Images

Protocol-Based Distributed Security Fusion Estimation for Time-Varying

2024-25_IMG_032
Uncertain Systems Over Sensor Networks: Tackling DoS Attacks

Toward Robust and Unconstrained Full Range of Rotation Head Pose

2024-25_IMG_033
Estimation

Field-to-Field Coordinate-Based Segmentation Algorithm on Agricultural

2024-25_IMG_034
Harvest Implements

Ensemble Image Explainable AI (XAI) Algorithm for Severe Community-

2024-25_IMG_035
Acquired Pneumonia and COVID-19 Respiratory Infections
 Edge-Computing-Enabled Deep Learning Approach for Low-Light Satellite
2024-25_IMG_036
Image Enhancement

2024-25_IMG_037 An Efficient Method for Detecting Dense and Small Objects in UAV Image

Conventional to Deep Ensemble Methods for Hyperspectral Image

2024-25_IMG_038
Classification: A Comprehensive Survey

Deep Evidential Remote Sensing Landslide Image Classification With a New

2024-25_IMG_039
Divergence, Multiscale Saliency and an Improved Three-Branched Fusion

Project ID Title

Detection of SAR Image Multiscale Ship Targetsin Complex Inshore Scenes

2024-25_IMG_040
Based on Improved YOLOv5

2024-25_IMG_041 AIROGS: Artificial Intelligence for Robust Glaucoma Screening Challenge

Eye-LRCN: A Long-Term Recurrent Convolutional Network for Eye Blink

2024-25_IMG_042
Completeness Detection

Learning Decentralized Traffic Signal Controllers with Multi-Agent Graph

2024-25_IMG_043
Reinforcement Learning

FsrGAN: A Satellite and Radar-Based Fusion Prediction Network for

2024-25_IMG_044
Precipitation Nowcasting

2024-25_IMG_045 Unsupervised Human Activity Recognition Learning for Disassembly Tasks

Exploring Deep Learning and Machine Learning Approaches for Brain

2024-25_IMG_046
Hemorrhage Detection

Automatic Accident Detection, Segmentation and Duration Prediction Using

2024-25_IMG_047
Machine Learning
Analysis of Brain Imaging Data for the Detection of Early Age Autism
2024-25_IMG_048 Spectrum Disorder Using Transfer Learning Approaches for Internet of
Things

Project ID Title

Deep Omni-supervised Learning for Rib Fracture Detection from Chest

2024-25_IMG_049
Radiology Images

A Deep Quantum Convolutional Neural Network Based Facial Expression

2024-25_IMG_050
Recognition For Mental Health Analysis

A Novel Grading Biomarker for the Prediction of Conversion from Mild

2024-25_IMG_051
Cognitive Impairment to Alzheimer’s Disease
Machine Learning Analysis of Human Skin by Optoacoustic Mesoscopy for
2024-25_IMG_052
Automated Extraction of Psoriasis and Aging Biomarkers
 Anomaly Detection for Medical Images Using Teacher–Student Model With
2024-25_IMG_053
Skip Connections Mingxuan Liu and Multiscale Anomaly Consistency
 Domain

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Domain

Image Processing

Image Processing

Image Processing

Image Processing
Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Domain

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing
Image Processing

Image Processing

Image Processing

Image Processing

Domain

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Image Processing

Domain

Image Processing

Image Processing

Image Processing

Image Processing
Image Processing
Project ID

2024-25_WSN_001

2024-25_WSN_002

2024-25_WSN_003

2024-25_WSN_004

2024-25_WSN_005

2024-25_WSN_006

2024-25_WSN_007

2024-25_WSN_008

2024-25_WSN_009

2024-25_WSN_010

2024-25_WSN_011

2024-25_WSN_012

2024-25_WSN_013

Project ID

2024-25_WSN_014

2024-25_WSN_015

2024-25_WSN_016

2024-25_WSN_017

2024-25_WSN_018

2024-25_WSN_019

2024-25_WSN_020

2024-25_WSN_021
2024-25_WSN_022

2024-25_WSN_023

2024-25_WSN_024

2024-25_WSN_025

2024-25_WSN_026

Project ID

2024-25_WSN_027

2024-25_WSN_028

2024-25_WSN_029

2024-25_WSN_030

2024-25_WSN_031

2024-25_WSN_032

2024-25_WSN_033

2024-25_WSN_034

2024-25_WSN_035

2024-25_WSN_036

2024-25_WSN_037

2024-25_WSN_038

2024-25_WSN_039

Project ID

2024-25_WSN_040

2024-25_WSN_041
2024-25_WSN_042

2024-25_WSN_043

2024-25_WSN_044

2024-25_WSN_045

2024-25_WSN_046

2024-25_WSN_047

2024-25_WSN_048

2024-25_WSN_049

2024-25_WSN_050

2024-25_WSN_051
Title

Unleashing Dynamic Pipeline Reconfiguration of P4 Switches for Efficient Network Monitoring

Capacitated Shortest Path Tour-Based Service Chaining Adaptive to Changes of Service Demand and
Network Topology

Deep Learning-based Design of Uplink Integrated Sensing and Communication

SDOA-Net: An Efficient Deep Learning-Based DOA Estimation Network for Imperfect Array

STAR-RIS-Assisted Communication Radar Coexistence: Analysis and Optimization

Networked Integrated Sensing and Communications for 6G Wireless Systems

Frequency-Selective Adversarial Attack Against Deep Learning-Based Wireless Signal Classifiers

Attacking and Defending Deep-Learning-Based Off-Device Wireless Positioning Systems

Towards Real-time Network Intrusion Detection with Image-based Sequential Packets Representation

AoI-aware Sensing Scheduling and Trajectory Optimization for Multi-UAV-assisted Wireless Backscatter
Networks
Experimental Demostration of a MIMO-OFDM Underwater Optical Communication System for
Reducing Alignment Angle Requirements
Enhancing Resource Utilization of Non-terrestrial Networks Using Temporal Graph-based
Deterministic Routing

A Novel Local and Hyper-Local Multicast Services Transmission Scheme for Beyond 5G Networks

Title

OFDM-Based Active STAR-RIS-Aided Integrated Sensing and Communication Systems

Robust Resource Allocation for STAR-RIS Assisted SWIPT Systems

A Meta-DDPG Algorithm for Energy and Spectral Efficiency Optimization in

STAR-RIS-Aided SWIPT

Deep Reinforcement Learning for Multi-User RF Charging with Non-linear Energy Harvesters

Analysis of IRS-Assisted Downlink Wireless Networks over Generalized Fading

Generalized Automatic Modulation Classification for OFDM Systems Under Unseen

Synthetic Channels
Enabling Deep Learning-based Physical-layer Secret Key Generation for FDD-OFDM Systems in
Multi-Environments

RL-based Relay Selection for Cooperative WSNs in the Presence of Bursty Impulsive Noise
Energy-Efficient Distributed Spiking Neural Network for Wireless Edge Intelligence

Control-Oriented Deep Space Communications For Unmanned Space Exploration

Super-Resolution Estimation of UWB Channels including the Dense Component — An SBL-Inspired Approach

Frequency-Switchable Routing Protocol for Dynamic Magnetic Induction-Based Wireless

Underground Sensor Networks

Optimized Routing Protocol Through Exploitation of Trajectory Knowledge for UAV Swarms

Title

A Safe Deep Reinforcement Learning Approach for Energy Efficient Federated Learning
in Wireless Communication Networks

Semantic Utility Loss of Information for Energy Efficient Semantic Status Update Communications

Hybrid Active-Passive RIS Transmitter Enabled Energy-Efficient Multi-User Communications

Privacy and Security in Ubiquitous Integrated Sensing and Communication: Threats, Challenges
and Future Directions

Decentralized Federated Learning: A Survey on Security and Privacy

Benefits of V2V communication in connected and autonomous vehicles in the presence of delays in
communicated signals

DeepSense-V2V: A Vehicle-to-Vehicle Multi-Modal Sensing, Localization, and Communications Dataset

A Dynamic and Efficient Self-Certified Authenticated Group Key Agreement Protocol for
VANET

Dynamic Cooperative MAC Optimization in RSU-Enhanced VANETs: A Distributed Approach

Intelligent Reflecting Surfaces Assisted Cellular V2X based Open RAN Communications

Performance Characterization of Joint Communication and Sensing with Beyond 5G NR-V2X Sidelink

End-to-End Autonomous Driving through V2X Cooperation

Unified End-to-End V2X Cooperative Autonomous Driving

Title

Virtual Sensor for Real-Time Bearing Load Prediction Using Heterogeneous Temporal Graph Neural Networks

FDA-MIMO Transmitter and Receiver Optimization

Joint Visibility Region and Channel Estimation for Extremely Large-Scale MIMO Systems

STAR-RIS Aided Secure MIMO Communication Systems

Integrated Sensing and Communication with Massive MIMO: A Unified Tensor Approach for
Channel and Target Parameter Estimation

Interleaved Training for Massive MIMO Downlink via Exploring Spatial Correlation

Exploiting Active RIS in NOMA Networks with Hardware Impairments

Covert Communication of STAR-RIS Aided NOMA Networks

Finite SNR Diversity-Multiplexing Trade-off in Hybrid ABCom/RCom-Assisted NOMA Systems

Achievable Rate Analysis of Intelligent Omni-Surface Assisted NOMA Holographic MIMO Systems

Power-Level-Design-aware Scalable Framework for Throughput Analysis of GF-NOMA in mMTC

MEL: Efficient Multi-Task Evolutionary Learning for High-Dimensional Feature Selection

 Domain

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Domain

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication
Communication

Communication

Communication

Communication

Communication

Domain

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Domain

Communication

Communication
Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication

Communication
Project ID

2024-25_BC_001

2024-25_BC_002

2024-25_BC_003

2024-25_BC_004

2024-25_BC_005

2024-25_BC_006

2024-25_BC_007

2024-25_BC_008

2024-25_BC_009

2024-25_BC_010

Project ID

2024-25_BC_011

2024-25_BC_012

2024-25_BC_013

2024-25_BC_014

2024-25_BC_015

2024-25_BC_016

2024-25_BC_017
2024-25_BC_018

2024-25_BC_019

2024-25_BC_020
Title

Security for the Metaverse: Blockchain and Machine Learning Techniques for Intrusion Detection

Defending Against Poisoning Attacks in Federated Learning with Blockchain

User Connection and Resource Allocation Optimization in Blockchain Empowered Metaverse

over 6G Wireless Communications

A User Based HVAC System Management Through Blockchain Technology and Model
Predictive Control

Enhancing Cloud Computing Security with Fast, Secure, and Anonymous Key Agreement:
Overcoming Bad Randomness for Improved Privacy

ProSecutor: Protecting Mobile AIGC Services on Two-Layer Blockchain via Reputation and
Contract Theoretic Approaches

Electronic Voting Using Block chain Technology

BIONIB: Blockchain-based IoT using Novelty Index in Bridge Health Monitoring

Blockchain-assisted Lightweight Authenticated Key Agreement Security Framework for Smart

Vehicles-enabled Intelligent Transportation System

S-MBDA: A Blockchain-based Architecture for Secure Storage and Sharing of Material Big-Data

Title

SC-CAAC: A Smart-Contract-Based Context-Aware Access Control Scheme for Blockchain-Enabled

IoT Systems

CRPWarner: Warning the Risk of Contract-related Rug Pull in DeFi Smart

Contracts

ISCSCLV: Improving Smart Contract Security with Contrastive Learning-based Vulnerability Detection

Collaborative Learning for Cyberattack Detection in Blockchain Networks

Secure and Efficient Federated Learning Through Layering and Sharding Blockchain

Safeguarding Patient Data-Sharing: Blockchain-Enabled Federated Learning in Medical

Diagnostics

PPBFL: A Privacy Protected Blockchain-based Federated Learning Model

zkFL: Zero-Knowledge Proof-based Gradient Aggregation for Federated Learning

Federated Learning Meets Blockchain in Decentralized Data Sharing: Healthcare Use Case

Distributed IIoT Anomaly Detection Scheme Based on Blockchain and Federated Learning
 Domain

Block Chain

Block Chain

Block Chain

Block Chain

Block Chain

Block Chain

Block Chain

Block Chain

Block Chain

Block Chain

Domain

Block Chain

Block Chain

Block Chain

Block Chain

Block Chain

Block Chain

Block Chain
Block Chain

Block Chain

Block Chain
Project ID

2024-25_CYS_001

2024-25_CYS_002

2024-25_CYS_003

2024-25_CYS_004

2024-25_CYS_005

2024-25_CYS_006

2024-25_CYS_007

2024-25_CYS_008

2024-25_CYS_009

2024-25_CYS_010

2024-25_CYS_011

2024-25_CYS_012

2024-25_CYS_013

Project ID

2024-25_CYS_014

2024-25_CYS_015

2024-25_CYS_016

2024-25_CYS_017

2024-25_CYS_018

2024-25_CYS_019

2024-25_CYS_020

2024-25_CYS_021

2024-25_CYS_022
2024-25_CYS_023

2024-25_CYS_024

2024-25_CYS_025

2024-25_CYS_026

Project ID

2024-25_CYS_027

2024-25_CYS_028

2024-25_CYS_029

2024-25_CYS_030

2024-25_CYS_031

2024-25_CYS_032

2024-25_CYS_033

2024-25_CYS_034

2024-25_CYS_035

2024-25_CYS_036

2024-25_CYS_037

2024-25_CYS_038

2024-25_CYS_039

Project ID

2024-25_CYS_040

2024-25_CYS_041

2024-25_CYS_042

2024-25_CYS_043

2024-25_CYS_044
2024-25_CYS_045

2024-25_CYS_046

2024-25_CYS_047

2024-25_CYS_048

2024-25_CYS_049

2024-25_CYS_050

2024-25_CYS_051

2024-25_CYS_052

Project ID

2024-25_CYS_053

2024-25_CYS_054

2024-25_CYS_055

2024-25_CYS_056

2024-25_CYS_057

2024-25_CYS_058

2024-25_CYS_059

2024-25_CYS_060

2024-25_CYS_061

2024-25_CYS_062

2024-25_CYS_063

2024-25_CYS_064

2024-25_CYS_065
Title

A Monolithic Cybersecurity Architecture for Power Electronic Systems

Utilizing Deep Learning for Enhancing Network Resilience in Finance

Applying Large Language Models to PowerSystems: Potential Security Threats

Multi-phase Quantum resistant Framework for Secure Communication in SCADA Systems

The Role of Deep Learning in Advancing Proactive Cybersecurity Measures for Smart Grid Networks

Modeling and Assessment of Cyber Attacks Targeting Converter-Driven Stability of Power Grids With PMSG-Based
Wind Farms

Resource-Constraint Deep Forest based Intrusion Detection Method in Internet of Things for Consumer Electronic

ECF-IDS: An Enhanced Cuckoo Filter-based Intrusion Detection System for In-vehicle Network

Advancing DDoS Attack Detection: A Synergistic Approach Using Deep Residual Neural Networks and Synthetic
Oversampling
Advancing DDoS Attack Detection: A Synergistic Approach Using Deep Residual Neural Networks and Synthetic
Oversampling

Defending Against Poisoning Attacks in Federated Learning with Blockchain

PEAE-GNN: Phishing Detection on Ethereum via Augmentation Ego-Graph Based on Graph Neural Network

TTPXHunter: Actionable Threat Intelligence Extraction as TTPs from Finished Cyber Threat Reports

Title

Revolutionizing Cyber Threat Detection With Large Language Models: A Privacy-Preserving

BERT-Based Lightweight Model for IoT/IIoT Devices

Classification and Characterization of Encoded Traffic in SCADA Network using Hybrid Deep Learning Scheme

A Situation Based Predictive Approach for Cybersecurity Intrusion Detection and Prevention Using Machine
Learning and Deep Learning Algorithms in Wireless Sensor Networks of Industry 4.0

Deep Learning in the Fast Lane: A Survey on Advanced Intrusion Detection Systems for Intelligent Vehicle Networks

Semantic Deep Hiding for Robust Unlearnable Examples

Secure Distributed Control for Demand Response in Power Systems Against Deception Cyber-Attacks With Arbitrary
Patterns

Modeling Load Redistribution Attacks in Integrated Electricity-Gas Systems

An Unsupervised Adversarial Autoencoder for Cyber Attack Detection in Power Distribution Grids

The Role of Deep Learning in Advancing Proactive Cybersecurity Measures for Smart Grid Networks
Quantized Distributed Economic Dispatch for Microgrids: Paillier Encryption-Decryption Scheme

Automated Knowledge-Based Cybersecurity Risk Assessment of Cyber-Physical Systems

Attribute-hiding fuzzy encryption for privacy-preserving data evaluation

Privacy-Preserving Naïve Bayesian Classification for Health Monitoring Systems

Title

Dynamic User Clustering for Efficient and Privacy-Preserving Federated Learning

The Role of Cyber-Physical-Social Systems in Smart Energy Future

Systematically Assessing the Security Risks of AI/ML-enabled Connected Healthcare Systems

Cyber-Physical Testbed Co-Simulation Real-Time: Normal and Abnormal System Frequency Response

A Game-Theoretical Scheme in the Smart Grid With Demand-Side Management: Towards a Smart Cyber-Physical
Power Infrastructure

Secure Relay Selection With Outdated CSI in Cooperative Wireless Vehicular Networks: A DQN Approach

Depriving the Survival Space of Adversaries Against Poisoned Gradients in Federated Learning

Learning Near-Optimal Intrusion Responses Against Dynamic Attackers

Trusted Operations of a Military Ground Robot in the Face of Man-in-the-Middle Cyberattacks Using Deep
Learning Convolutional Neural Networks: Real-Time Experimental Outcomes

Optimal Finite Horizon Scheduling of Wireless Networked Control Systems

DARD: Deceptive Approaches for Robust Defense Against IP Theft

The Least Increasing Aversion (LIA) Protocol: Illustration on Identifying Individual Susceptibility to
Cybersickness Triggers

Temporal Characterization and Prediction of VR Traffic: A Network Slicing Use Case

Title

Gotham Testbed: A Reproducible IoT Testbed for Security Experiments and Dataset Generation

A Situation Based Predictive Approach for Cybersecurity Intrusion Detection and Prevention Using Machine
Learning and Deep Learning Algorithms in Wireless Sensor Networks of Industry 4.0

Deep Learning in the Fast Lane: A Survey on Advanced Intrusion Detection Systems forIntelligent Vehicle Networks

Semantic Deep Hiding for Robust Unlearnable Examples

Secure Distributed Control for Demand Response in Power Systems AgainstDeception Cyber-Attacks With Arbitrary
Patterns
Modeling Load Redistribution Attacks in Integrated Electricity-Gas Systems

An Unsupervised Adversarial Autoencoder forCyber Attack Detection in Power Distribution Grids

The Role of Deep Learning in Advancing Proactive Cybersecurity Measures for Smart Grid Networks

Quantized Distributed Economic Dispatch for Microgrids: Paillier Encryption-Decryption Scheme

Automated Knowledge-Based Cybersecurity Risk Assessment of Cyber-Physical Systems

Attribute-hiding fuzzy encryption for privacy-preserving data evaluation

Privacy-Preserving Naïve Bayesian Classification for Health Monitoring Systems

Dynamic User Clustering for Efficient and Privacy-Preserving Federated Learning

Title

The Role of Cyber-Physical-Social Systems in Smart Energy Future

Systematically Assessing the Security Risks of AI/ML-enabled Connected Healthcare Systems

Cyber-Physical Testbed Co-Simulation Real-Time:Normal and Abnormal System Frequency Response

A Game-Theoretical Scheme in the Smart Grid With Demand-Side Management:Towards a Smart Cyber-Physical
Power Infrastructure

Secure Relay Selection With Outdated CSI in Cooperative Wireless Vehicular Networks: A DQN Approach

Depriving the Survival Space of Adversaries Against Poisoned Gradients in Federated Learning

Learning Near-Optimal Intrusion Responses Against Dynamic Attackers

Trusted Operations of a Military Ground Robot in the Face of Man-in-the-Middle Cyberattacks Using Deep
Learning Convolutional Neural Networks: Real-Time Experimental Outcomes

Optimal Finite Horizon Scheduling of Wireless Networked Control Systems

DARD: Deceptive Approaches for Robust Defense Against IP Theft

The Least Increasing Aversion (LIA) Protocol: Illustration on Identifying Individual Susceptibility to Cybersickness
Triggers

Temporal Characterization and Prediction of VR Traffic: A Network Slicing Use Case

Gotham Testbed: A Reproducible IoT Testbed for Security Experiments and Dataset Generation
 Domain

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Domain

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security
Cyber Security

Cyber Security

Cyber Security

Cyber Security

Domain

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Domain

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security
Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Domain

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security

Cyber Security