Iit kgp workshop
Download as PPTX, PDF1 like383 views
This document discusses research into human-in-loop cyber-physical systems using internet-of-things technologies. It describes a platform called RIPSAC that integrates sensor data from physical objects, infrastructure and humans to provide intelligent services. Example applications discussed include elderly monitoring, activity detection, and integrating data from various smart domains like transportation, healthcare and utilities. The document also outlines several research projects in areas like healthcare monitoring using mobile phones, new sensing techniques like 5-senses computing, distributed edge computing, and knowledge-driven analytics using semantic sensor descriptions.
Iit kgp workshop
- 1. Experience certainty. Copyright © 2011 Tata Consultancy Services Limited Human-in-loop Cyber-physical Systems - Intelligent Infrastructure using Internet-of-Things Arpan Pal Head of Research Innovation Lab, Kolkata
- 3. 3 Experience certainty. Human-in-Loop Cyber-physical Systems Humans Physical Objects and Infrastructure Computing Infrastructure Physical Context Discovery
- 4. 4 Experience certainty. Signal Processing Internet-of-Things - towards Intelligent Infrastructure Sense Extract Analyze Respond Learn Monitor Intelligent Infra @Home @Building @Vehicle @Utility @Mobile @Store @Road “Intelligent” (Cyber) “Infrastructure” (Physical) APPLICATION SERVICES BACK-END PLATFORM INTERNET GATEWAY Sense Extract Analyze Respond Communication Computing
- 5. 5 Challenges and Solution Approach Systems • Making Sensing Unobtrusive and Pervasive • Sensing the Human Context Cloud-based Sensor Data Analytics Platform Use of Mobile phones and Cameras as sensing devices New Sensors for human context – EEG, 5 senses computing Signal Processing • Preserving the Battery power of edge devices • Extracting information from ambient-noise-corrupted sensor data Low-power computing algorithms Adaptive Signal Processing for Ambient Noise Removal Communication • Reducing the cost of Communication while preserving reliability and security • Preserving the Privacy Secure, Lightweight yet Reliable communication protocols over Internet Quantifying Privacy vs. Utility measures Computing • Knowledge and Model Driven Analytics in Real-time Distributed Computing - Bringing Edge into the Grid Semantics driven Analytics - Reasoning and Semantic Sensor Web Model driven Analytics - Cyber-physical system modeling / Human behavior modeling
- 6. 6 Integrated Platform for Intelligent Infrastructure People Feedback & Emotions Social Media Integrated Services Sensors & IoT Platform Traditional Monitoring & Control Systems Citizen Data Smart Integration Platform Transportation Healthcare Electricity WaterPublic Safety Tourism Smart Integrated Services Sense Analyze Extract Respond Intelligence Smart Domain Services Community etc. Sense: People Activity, Appliances, Vehicles , Road, Home/Bldg, Utility Infrastructure Detect gas leakage/water contamination : mobilize rescue team, suggest optimum route Divert Road Traffic in case of Water Pipeline Burst Correlate Electricity/Water /Gas consumption patterns Intelligent Integration Platform Integrated Intelligent Services RIPSAC – Real-time Integrated Platform Services & Analytics for Cyber-physical Systems
- 7. 7 Platform Architectural Layers Internet End Users & Renderers Administrators Device Integration & Management Services Analytics Services Application Services Storage Messaging & Event Distribution Services ApplicationServices Presentation Services Application Support Services OS & Device Drivers Sensor Signal Processing Middleware Middleware(Security/PrivacyandProtocols) Edge Gateway Sensors Internet Back-end
- 8. 8 Experience certainty. Cyber Physical System – Research Theme RIPSAC Infrastructure Simulation New Sensing Platforms, 5 Senses Computing Energy Water Transportation Security & Privacy Distributed Computing Facilities Data Integration & Visualization Safety Buildings Home City Vehicles Non revenue water Long term network expansion Renewable sources Energy conservations Intelligent Infrastructures Sensor Informatics for Home Sensor Informatics for Vehicular Monitoring Transport planning Electricity Grid Optimization algorithms Big data Communications & Sensor Informatics
- 9. 9 Experience certainty. Human-in-Loop Cyber-physical System – Research Theme RIPSAC 2D/3d Surveillance - Kinect Physiological Sensing – ECG, EEG, … Physiology Identity Smartphone Sensors – GPS, Accelerometer, Magentometer, Gyropscope, Camera, Mic Healthcare • Elderly People Monitoring • Chronic Disease People Monitoring Personalized learning • Cognitive Load Web and Social Media Smart Meters Wellness • Fitness • Stress, Fatigue Organizational Behavior • Personal Physical Network Discovery • Team Efficiency / Best Practice Analysis Retail • Customer Behavior Study Driving • Stress • Fatigue
- 10. Research Projects – Ubiquitous Healthcare
- 11. 11 Intelligent Healthcare – Elderly / Chronic Patient Monitoring ECG Blood Pressure Monitor Pulse OxyMeter Mobile phone as medical gateway Patient Records Health Center / Home Expert Doctor • 2 papers in SMART 2012 and MobiHoc 2012 • Requirement from NUH (Peritonial Dialysis) and SingHealth (Elderly Care)
- 12. 12 Intelligent Healthcare – Elderly / Chronic Patient Monitoring Mobile phone as medical Sensor Patient Records Health Center / Home Expert Doctor • Replace Medical Sensors with Mobile Phone Sensing • Activity and Localization using Mobile Phones • Activity and Identification using Kinect Camera • Social Media as a Soft sensor • Multimodal Fusion Identification, Localization and Activity Detection • 1 paper in UbiComp 2013
- 13. 13 PPG based Pulse Measurement using Phone Camera Subject1 Subject2 Subject3 Actual Detected Actual Detected Actual Detected 68 66 66 63 85 84 2.9% 4.5% 1.1% Subject Actual Pulse Rate Detected Pulse Rate (20 sec skip) Detected Pulse Rate (automatic detection) PSNR (automatic detection) A 54 53.542 53.542 22.887 B 66 63.404 63.404 15.351 C 84 84.539 84.539 19.831 D 106 98.629 98.629 21.741 E 80 88.062 88.062 14.788 F 105 102.15 102.15 16.705 G 105 38.747 0 0 H 80 42.27 0 0 • 1 paper in Mobihoc 2013 • 1 patent filed TCS Fit4LIfe Pilot
- 14. 14 Blood Pressure and ECG Monitoring from PPG Extract PPG Features BP Ground Truth Create BP Model Extract PPG Features Predict BP levels (SP, DP, PP) Extract ECG Features Create ECG Parameters’ Model Predict ECG Parameters ECG Parameters BP levels (SP, DP, PP) Training Phase Testing Phase Data set Pd Ps PP-diff < 15 Standard dataset with 14 PPG features 92.9% 74.7% 77.9% TCS recorded dataset with 14 PPG features + height, weight, age 99.3% 82.7% 85.5% BP Level Pd Ps Very Low < 50 < 70 Low 50-65 70-100 Normal 65-90 100- 135 High 90-100 135- 160 Very High > 100 >160
- 15. 15 Mobile Phone based Activity Detection and Localization Activity Detection – Uses Accelerometer Data – Gyroscope and Magnetometer for orientation correction – Step Count, Stride Length Estimation – Walking, Brisk Walking, Running Classification Indoor Localization – Initial Referencing through GPS and Magnetometer – Inertial Navigation through accelerometer, gyro, magnetometer – Improved accuracy through Stride Length, Kalman Filter / Particle Filter – Tracking of non-smartphones via Bluetooth Location ID LOC I LOC II LOC III Actual (ft) 2 4 6 Estimated (ft) 1.95 4.16 6.27 % Error 2.5 4.12 4.4 • 1 paper in UbiComp 2013 • 3 patents filed Activity Detection for TCS Fit4Life Generalized indoor localization – Colleague Finder, Retail, Emergency Evacuation
- 16. 16 Kinect Based Identification and Activity Detection Human Identification – Skeleton Model Based / Depth based – External Stimulus based refinement – Accuracy of 90% for less than 10 people database • 2D Camera with IR depth sensor • Excitation by IR light pattern • Directional Mic. Activity Detection – Enter/leave a room – Sitting / Standing / Walking / Lying down – Going to Bathroom – Taking Medicine LIRIS human activities dataset • 4 papers in Fuzz IEEE 2013 , CEC 2013, UbiComp 2013, SMC 2013 • 2 patents filed
- 17. 17 Social Media as a Soft-sensor for Healthcare Support Community Discovery – Use hidden community detection by applying NLP on posts to create the social graph to identify the undeclared community for a given disease Disease onset discovery like dementia or Alzheimer's disease or psychological disorders from social network posts – Search for patterns in posts to detect possible symptoms to diseases – E.g. - sentiment analysis on posts will give whether the given post’s emotion is positive or negative. If the emotions are cycling between positive and negative extremes with some periodicity, probably the person has bipolar disorder • 1 paper in UbiComp 2012
- 18. Research Projects – New Sensing Techniques
- 19. 19 Experience certainty. Bio-sensing for Cognitive Load User Study Biased and Indirect Biological Response using EEG Unbiased & more reliable method • 2 papers in Fuzz IEEE 2013 , SMC 2013 • 2 patents filed • Can be used for Usability Testing of GUI
- 20. 20 Experience certainty. 5 senses Computing - 3D Reconstruction with 2D images from mobiles • Low cost solution for 3D reconstruction from multiple 2D images captured from mobile device. • Derive the motion information from the inbuilt sensors of the mobile phone and then aid in increasing the accuracy of the 3D reconstruction. • Dynamic 3D reconstruction in outdoor environment which is not possible using a Kinect. • 3D reconstruction of homogeneous objects • Future research focus on the multi-modal fusion of the 3D information and the other sensors’ data for a given object or environment Applications • Agro-advisory Service • Remote Diagnostics of Machines • Remote Healthcare • 1 paper in VISAPP 2012
- 21. Research Projects – Communication and Computing
- 22. 22 Experience certainty. Grid with an Edge • CPU utilization better in Condor • Condor performs better with more nodes • Further advantages w.r.t Heterogeneity, Versatility, Matchmaking & scheduling • 3 papers in NGMAST 2012, PDPTA 2013, WiMob 2013 • 2 patents filed • Flavio Bonomi et.al. MCC2012, Helsinki, Finland
- 23. 23 Experience certainty. Communication Aspect- Replace HTTP Constrained Object Access Protocol (CoAP) Improved version of CoAP using dynamic network condition sensing Lightweight security protocols sensor authentication and data delivery Use suitable lightweight application protocol between edge devices and core network • 3 papers in ICDCN 2013, ICNC 2013, WPMC 2013 • 2 patents filed
- 24. 24 Experience certainty. Knowledge-driven Analytics Ontology and Description for Sensors • Non-standard / Multi-standard sensor descriptions across multi-domains • Bringing all sensor data in common semantic form • Semantic Sensor Web (OGC-SWE) • Will provide ease of sensor discovery Ontology and Knowledge based Reasoning • Reasoning over continuously flowing (streaming) facts • Reasoning over streaming data is integrated with “background knowledge” (static unchanging or slowly changing knowledge • Spatio-temporal Queries Semantic Analytics • Analytics-as-a-Service • Query language to specify processing workflow on Time series data • 5 papers in ICST 2012 , ICNC 2013, ICUIMC 2013, ODBASE 2013, KES 2013 • 4 patents filed
- 25. 25 Experience certainty. Privacy Preservation • Information-theoretic approach for sensitivity analysis of sensor data • Requirement based application utility measurement • Balancing of Privacy vs. Utility Privacy Utility • 1 paper in SecurIT 2012 • 2 patents filed Privacy Preservation Tool
- 26. 26 Lab-at-a-Glance Research Areas • Sensor Signal Processing • 2D/ 3D Image / Video Processing • Protocols, Security and Privacy • Parallel and Distributed Computing • Stream Processing and Reasoning • System Modeling and Identification • Sematic Sensor Web • Social Media Analytics Academic Collaborations • Singapore Management University (iCity Platform) • Indian Statistical Institute (Protocol/Privacy/Security, Image / Video Processing) • IIT Kharagpur (Analytics, Semantic Processing) • IIT Bombay (Energy and Utilities) • Jadavpur University (Signal Processing) Higher Studies • PhD - 4 • Masters - 4 Total Researchers - 37
Editor's Notes
- #6: Buiness Application