Machine learning (ML) shows strong performance in making accurate inferences from massive, high-dimensional data. Many scientists turn to this new tool when traditional inferential procedures cannot deal with overly messy data and complex target phenomena. One example is galactic archaeology, a branch of astronomy that aims to unravel the epic history of the Milky Way using the present snapshot of stars with only a handful of physical parameters. Historical inference in galactic archaeology is difficult due to the uncertainty (...) of what counts as evidence of past events. While ML is expected to help address such challenging situations, it comes with its own epistemological limitations. Two issues, theory-ladenness and non-uniqueness, can undermine the evidential power of ML outcomes in scientific inferences. ML’s success in aiding Galactic archaeology teaches lessons about how it can serve key epistemic functions for the historical sciences, unaffected by those two issues. I show that ML can empower the evidence-gathering procedure in science, not by outputting data to be directly taken as evidence, but as evidential constraints: ML partitions and structures data for it to be subsequently interpreted as evidence with the help of domain knowledge and inferential procedures. Used in this way, ML not only provides a solution to the ambiguity of historical evidence but also avoids its own epistemic limitations. This use of ML can be generalized to other historical sciences that engage with big data and automated inference. (shrink)

Prediction-based decisions, which are often made by utilizing the tools of machine learning, influence nearly all facets of modern life. Ethical concerns about this widespread practice have given rise to the field of fair machine learning and a number of fairness measures, mathematically precise definitions of fairness that purport to determine whether a given prediction-based decision system is fair. Following Reuben Binns (2017), we take ‘fairness’ in this context to be a placeholder for a variety of (...) normative egalitarian considerations. We explore a few fairness measures to suss out their egalitarian roots and evaluate them, both as formalizations of egalitarian ideas and as assertions of what fairness demands of predictive systems. We pay special attention to a recent and popular fairness measure, counterfactual fairness, which holds that a prediction about an individual is fair if it is the same in the actual world and any counterfactual world where the individual belongs to a different demographic group (cf. Kusner et al. (2018)). (shrink)

Current methods of operationalizing concepts of misinformation in machine learning are often problematic given idiosyncrasies in their success conditions compared to other models employed in the natural and social sciences. The intrinsic value-ladenness of misinformation and the dynamic relationship between citizens' and social scientists' concepts of misinformation jointly suggest that both the construct legitimacy and the construct validity of these models needs to be assessed via more democratic criteria than has previously been recognized.

Data normalization is a crucial step in database management systems (DBMS), ensuring consistency, minimizing redundancy, and enhancing query performance. Traditional methods of normalization in supermarket sales databases often demand significant manual effort and domain expertise, making the process time-consuming and prone to errors. This paper introduces an innovative machine learning (ML)-based framework to automate data normalization in supermarket sales databases. The proposed approach utilizes both supervised and unsupervised ML techniques to identify functional dependencies, detect anomalies, and suggest optimal (...) schema transformations. Experiments on supermarket sales datasets show substantial improvements in accuracy, scalability, and processing time compared to traditional approaches. The results emphasize the potential of incorporating ML into database management practices to boost operational efficiency and support better decision-making. (shrink)

This paper presents a machine learning-based framework for real-time short-term snowfall forecasting by integrating atmospheric and topographic data. The model uses real-time meteorological data such as temperature, humidity, and pressure, along with terrain data like elevation and land cover, to predict snowfall occurrence within a 12-hour forecast window. Random Forest (RF) and Support Vector Machine (SVM) models are employed to process these multi-source inputs, demonstrating a significant improvement in prediction accuracy over traditional methods. Experimental results show that (...) the RF model achieved a root mean square error (RMSE) of 3.2 cm, while traditional regression models achieved an RMSE of 5.1 cm. The proposed framework provides a more reliable and accurate tool for real-time snowfall prediction, especially in mountainous regions, and can be deployed for operational weather forecasting applications. (shrink)

Machine learning algorithms may radically improve our ability to diagnose and treat disease. For moral, legal, and scientific reasons, it is essential that doctors and patients be able to understand and explain the predictions of these models. Scalable, customisable, and ethical solutions can be achieved by working together with relevant stakeholders, including patients, data scientists, and policy makers.

This study employs machine learning to predict diabetes using a Kaggle dataset with 13 features. Our three-layer model achieves an accuracy of 98.73% and an average error of 0.01%. Feature analysis identifies Age, Gender, Polyuria, Polydipsia, Visual blurring, sudden weight loss, partial paresis, delayed healing, irritability, Muscle stiffness, Alopecia, Genital thrush, Weakness, and Obesity as influential predictors. These findings have clinical significance for early diabetes risk assessment. While our research addresses gaps in the field, further work is needed (...) to enhance model generalizability. (shrink)

Just as humans can draw conclusions responsibly or irresponsibly, so too can computers. Machine learning systems that have been trained on data sets that include irresponsible judgments are likely to yield irresponsible predictions as outputs. In this paper I focus on a particular kind of inference a computer system might make: identification of the intentions with which a person acted on the basis of photographic evidence. Such inferences are liable to be morally objectionable, because of a way in (...) which they are presumptuous. After elaborating this moral concern, I explore the possibility that carefully procuring the training data for image recognition systems could ensure that the systems avoid the problem. The lesson of this paper extends beyond just the particular case of image recognition systems and the challenge of responsibly identifying a person’s intentions. Reflection on this particular case demonstrates the importance (as well as the difficulty) of evaluating machine learning systems and their training data from the standpoint of moral considerations that are not encompassed by ordinary assessments of predictive accuracy. (shrink)

Simple idealized models seem to provide more understanding than opaque, complex, and hyper-realistic models. However, an increasing number of scientists are going in the opposite direction by utilizing opaque machine learning models to make predictions and draw inferences, suggesting that scientists are opting for models that have less potential for understanding. Are scientists trading understanding for some other epistemic or pragmatic good when they choose a machine learning model? Or are the assumptions behind why minimal models (...) provide understanding misguided? In this paper, using the case of deep neural networks, I argue that it is not the complexity or black box nature of a model that limits how much understanding the model provides. Instead, it is a lack of scientific and empirical evidence supporting the link that connects a model to the target phenomenon that primarily prohibits understanding. (shrink)

In the contemporary world, there is lot of research going on in creating novel nano materials that are essential for many industries including electronic chips and storage devices in cloud to mention few. At the same time, there is emergence of usage of machine learning (ML) for solving problems in different industries such as manufacturing, physics and chemical engineering. ML has potential to solve many real world problems with its ability to learn in either supervised or unsupervised means. (...) It is inferred from the state of the art that that it is essential to use ML methods for analysing imagery of nano materials so as to ascertain facts further towards characterization and analysis of microstructure and spectral data of materials. Towards this end, in this paper, we proposed a ML based methodology for STEM image analysis and spectral data analysis from STEM image of a nano material. We proposed an algorithm named Machine Learning for STEM Image Analysis (ML-SIA) for analysing STEM image of a nano material. We proposed another algorithm named Machine Learning for STEM Image Spectral Data Analysis (ML-SISDA) for analysing spectral data of STEM image of a nano material. We developed a prototype ML application to implement the algorithms and evaluate the proposed methodology. Experimental results revealed that the ML based approaches are useful for characterization of nano materials. Thus this research helps in taking this forward by triggering further work in the area of material analysis with artificial intelligence. (shrink)

Issues of reliability are claiming center-stage in the epistemology of machine learning. This paper unifies different branches in the literature and points to promising research directions, whilst also providing an accessible introduction to key concepts in statistics and machine learning – as far as they are concerned with reliability.

With the rapid evolution of information technology, malware has become an advanced cybersecurity threat, targeting computer systems, smart devices, and large-scale networks in real time. Traditional detection methods often fail to recognize emerging malware variants due to limitations in accuracy, adaptability, and response time. This paper presents a comprehensive review of machine learning algorithms for real-time malware detection, categorizing existing approaches based on their methodologies and effectiveness. The study examines recent advancements and evaluates the performance of various (...) class='Hi'>machine learning techniques in detecting malware with minimal false positives and improved scalability. Additionally, key challenges, such as adversarial attacks, computational overhead, and real-time processing constraints, are discussed, along with potential solutions to enhance detection capabilities. An empirical evaluation is conducted to assess the effectiveness of different machine learning models, providing insights for future research in real-time malware detection. Keywords: Real-t. (shrink)

As more objections have been raised against grant peer-review for being costly and time-consuming, the legitimate question arises whether machine learning algorithms could help assess the epistemic efficiency of the proposed projects. As a case study, we investigated whether project efficiency in high energy physics can be algorithmically predicted based on the data from the proposal. To analyze the potential of algorithmic prediction in HEP, we conducted a study on data about the structure and outcomes of HEP experiments (...) with the goal of predicting their efficiency. In the first step, we assessed the project efficiency using Data Envelopment Analysis of 67 experiments conducted in the HEP laboratory Fermilab. In the second step, we employed predictive algorithms to detect which team structures maximize the epistemic performance of an expert group. For this purpose, we used the efficiency scores obtained by DEA and applied predictive algorithms – lasso and ridge linear regression, neural network, and gradient boosted trees – on them. The results of the predictive analyses show moderately high accuracy, indicating that they can be beneficial as one of the steps in grant review. Still, their applicability in practice should be approached with caution. Some of the limitations of the algorithmic approach are the unreliability of citation patterns, unobservable variables that influence scientific success, and the potential predictability of the model. (shrink)

Production scheduling represents a critical function within manufacturing and industrial operations, exerting a direct influence on productivity, operational efficiency, and overall cost management. Traditional scheduling methodologies, while foundational,often exhibit limitations when confronted with the complexity, variability, and dynamic demands of contemporary production environments. In response, this paper investigates the potential of Machine Learning (ML) techniques for the enhancement of production scheduling outcomes. Specifically, it examines the capabilities of reinforcement learning, neural networks, and genetic algorithms to model complex (...) systems, adapt to real-time disruptions, and support more effective decision-making processes. The paper furtherreviews notable industrial applications of these techniques, critically evaluating their performance relative to conventional methods. In addition, it addresses the inherent challenges associated with the deployment of ML in production scheduling, including data availability, algorithmic interpretability, and integration with legacy systems. Finally, the study outlines future research directions, emphasizing the need for more robust, scalable, and interpretable ML-based scheduling solutions to meet the evolving demands of modern industry. (shrink)

The use of AI algorithms in criminal trials has been the subject of very lively ethical and legal debates recently. While there are concerns over the lack of accuracy and the harmful biases that certain algorithms display, new algorithms seem more promising and might lead to more accurate legal decisions. Algorithms seem especially relevant for bail decisions, because such decisions involve statistical data to which human reasoners struggle to give adequate weight. While getting the right legal outcome is a strong (...) desideratum of criminal trials, advocates of the relational theory of procedural justice give us good reason to think that fairness and perceived fairness of legal procedures have a value that is independent from the outcome. According to this literature, one key aspect of fairness is trustworthiness. In this paper, I argue that using certain algorithms to assist bail decisions could increase three diferent aspects of judges’ trustworthiness: (1) actual trustworthiness, (2) rich trustworthiness, and (3) perceived trustworthiness. (shrink)

This work explores the potential of big data analytics, natural language processing (NLP), and machine learning (ML) techniques in predicting cyberbullying on social media. By analyzing large-scale datasets consisting of user comments, posts, and interactions, the study aims to detect harmful content patterns, abusive language, and behavioral trends that indicate cyberbullyingThe rapid proliferation of social media has transformed communication and interaction, but it has also led to an alarming rise in cyberbullying incidents. Cyberbullying, characterized by repeated and intentional (...) harassment through digital platforms, has significant psychological and social consequences for victims, often leading to anxiety, depression, and even self-harm. Traditional methods of identifying and mitigating cyberbullying are often reactive and inefficient due to the vast volume of data generated across multiple platforms. Therefore, predictive models leveraging big data and artificial intelligence (AI) offer a proactive approach to detecting and preventing online harassment. Sentiment analysis, text classification, and deep learning models such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are employed to enhance the accuracy of cyberbullying predictions. Additionally, graph-based techniques are utilized to examine social network structures and identify potential perpetrators and victims based on interaction patterns. Despite the promising potential of big datadriven approaches, challenges such as data privacy, ethical concerns, and algorithmic bias must be addressed to ensure fair and responsible implementation. The study also highlights the importance of real-time monitoring systems that can alert platform administrators or authorities when cyberbullying behavior is detected. The findings demonstrate that integrating AI with big data analytics significantly improves the accuracy and efficiency of cyberbullying detection, enabling early intervention and fostering a safer digital environment. Future research will focus on refining detection models to handle multilingual data, cultural nuances, and evolving forms of cyberbullying across diverse social media platforms. (shrink)

Autonomous systems, powered by machine learning (ML), have the potential to revolutionize various industries, including transportation, healthcare, and robotics. However, the integration of machine learning in autonomous systems raises significant challenges related to safety, ethics, and regulatory compliance. Ensuring the reliability and trustworthiness of these systems is crucial, especially when they operate in environments with high risks, such as self-driving cars or medical robots. This paper explores the intersection of machine learning and autonomous systems, (...) focusing on the challenges of ensuring safety, mitigating ethical concerns, and navigating evolving regulatory frameworks. We discuss key strategies for improving the transparency, fairness, and accountability of autonomous systems, as well as the role of machine learning in enabling safe decision-making. Additionally, we propose a roadmap for the future development of autonomous systems that incorporates robust safety measures, ethical guidelines, and regulatory compliance. (shrink)

The meteoric rise of artificial intelligence (AI) has reshaped human society, enabling machines to perform tasks once deemed the exclusive domain of human cognition, from navigating complex urban landscapes to crafting eloquent prose. Yet, a profound philosophical question looms: Can these systems possess intentionality, the capacity to direct actions toward goals, beliefs, or desires with the nuanced depth of human consciousness? Franz Brentano defined intentionality as the "aboutness" of mental states, a quality intrinsic to human experience. This paper embarks on (...) an ambitious exploration of whether AI can transcend its algorithmic foundations to embody genuine intentionality, or whether it is destined to remain a sophisticated mimic, parroting intelligence without grasping its essence. Drawing on Ludwig Wittgenstein's concept of "forms of life," which posits that meaning arises from shared social and cultural contexts, I interrogate the contextual deficits that limit machine understanding. Through in-depth case studies of autonomous vehicles, large language models, Sniper the African grey parrot, and speculative scenarios such as AI-driven cultural preservation and interstellar diplomacy, I analyze the chasm between machine performance and human-like intentionality. This paper propose a groundbreaking framework for AI design, integrating dynamic learning, ethical embedding, and the novel concept of "synthetic forms of life," where machines might develop quasi-intentional states through prolonged, adaptive interactions with humans. By synthesizing insights from philosophy, cognitive science, neuroscience, and computer science, we argue that while current AI systems excel at simulating intelligence, they fall short of true intentionality due to their lack of lived experience. However, emerging paradigms like neuromorphic computing and embodied AI offer tantalizing possibilities for machines that might approximate meaning in ways that challenge our understanding of intelligence itself. This exploration poses a provocative question: If machines learn to "mean" something, will they redefine what it means to be human? Through rigorous analysis, technical depth, and speculative foresight, I aim to spark a reimagining of AI's potential and its implications for humanity's future. (shrink)

The Agricultural Portal is an innovative platform designed to improve crop production by providing farmers with easy access to agricultural information, resources, and tools. The portal offers a wide range of features including weather forecasts, crop shopping, crop prediction, yield prediction, crop stock and purchase History. This technical paper outlines the development and implementation of the Agricultural Portal, highlighting its features and functionalities. The paper also explores the benefits of the portal for farmers, including increased productivity, improved decision-making, and enhanced (...) profitability. Advanced machine learning models are integrated into the portal to improve its predictive capabilities. The portal is built on a robust technology platform that is scalable and adaptable to the needs of farmers of different sizes and geographies. The Agricultural Portal represents a significant step forward in the use of technology in agriculture. By providing farmers with easy access to information and resources, it has the potential to transform the way they farm and improve crop production across the globe by using different Machine Learning Algorithms. In the existing system There is only one feature but we are trying to add extra features and making into a single portal in the proposed system. (shrink)

Judgments of misinformation are made relative to the informational preferences of the communities making them. However, informational standards change over time, inducing distribution shifts that threaten the adequacy of machine learning models of misinformation. After articulating five kinds of distribution shifts, three solutions for enhancing success are discussed: larger static training sets, social engineering, and dynamic sampling. I argue that given the idiosyncratic ontology of misinformation, the first option is inadequate, the second is unethical, and thus the third (...) is superior. However, I conclude that the prospects for machine learning models of misinformation are far weaker than most have presupposed, given that both epistemic and non-epistemic values are difficult to operationalize dynamically in machine code, rendering them surprisingly at most a species of recommender systems rather than literal truth detectors. (shrink)

Typically, fair machine learning research focuses on a single decision maker and assumes that the underlying population is stationary. However, many of the critical domains motivating this work are characterized by competitive marketplaces with many decision makers. Realistically, we might expect only a subset of them to adopt any non-compulsory fairness-conscious policy, a situation that political philosophers call partial compliance. This possibility raises important questions: how does partial compliance and the consequent strategic behavior of decision subjects affect the (...) allocation outcomes? If k% of employers were to voluntarily adopt a fairness-promoting intervention, should we expect k% progress (in aggregate) towards the benefits of universal adoption, or will the dynamics of partial compliance wash out the hoped-for benefits? How might adopting a global (versus local) perspective impact the conclusions of an auditor? In this paper, we propose a simple model of an employment market, leveraging simulation as a tool to explore the impact of both interaction effects and incentive effects on outcomes and auditing metrics. Our key findings are that at equilibrium: (1) partial compliance by k% of employers can result in far less than proportional (k%) progress towards the full compliance outcomes; (2) the gap is more severe when fair employers match global (vs local) statistics; (3) choices of local vs global statistics can paint dramatically different pictures of the performance vis-a-vis fairness desiderata of compliant versus non-compliant employers; (4) partial compliance based on local parity measures can induce extreme segregation. Finally, we discuss implications for auditors and insights concerning the design of regulatory frameworks. (shrink)

Integrating medical imaging with computing technologies, such as Artificial Intelligence (AI) and its subsets: Machine learning (ML) and Deep Learning (DL) has advanced into an essential facet of present-day medicine, signaling a pivotal role in diagnostic decision-making and treatment plans (Huang et al., 2023). The significance of medical imaging is escalated by its sustained growth within the realm of modern healthcare (Varoquaux and Cheplygina, 2022). Nevertheless, the ever-increasing volume of medical images compared to the availability of imaging (...) experts. Biomedical experts and radiologists have resulted in a widening disparity, causing an excess and overwhelming workload on these healthcare professionals (Chen et al., 2021). Several studies indicate that the present-day biomedical radiologist is now saddled with the daunting task of interpreting an image almost every 10 seconds to keep pace with the burgeoning clinical demands (McDonald et al., 2015; Hosny et al., 2018; Lantsman et al., 2022). This cognitive drain has invariably led to inevitable consequences such as delays in diagnosis and an amplified risk of diagnostic errors – thus, the biomedical imaging aspect is in dire need of methods that would aid accurate diagnostics and analytics for improved decision making. In this review, the importance of AI-related technologies such as ML and/or DL methods are reviewed in relation to the processing of medical or biomedical images along with their potentials, challenges, and possible suggestions for future studies in the health landscape. The focus will be on machine learning methods associated with the medical field of image classification. (shrink)

Alzheimer's disease (AD) poses a significant public health challenge. The hippocampus is one of the most affected brain regions and a readily accessible biomarker for diagnosis through MRI imaging in machine learning applications. However, utilizing entire MRI image slices in machine learning for AD classification has shown reduced accuracy. This study introduces the novel 'select slices' method, which involves identifying and focusing on specific landmarks within the hippocampus region in MRI images. This approach aims to improve (...) classification accuracy by eliminating irrelevant information from the analysis. Our research aims to identify which views of MRI images produce higher accuracy for AD classification. We used multiclass classification using the publicly available Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, utilising Resnet50 and LeNet models to evaluate the value of three specific views (sagittal, coronal, and axial) and categories (normal, mild, and severe AD). The dataset comprised 4,500 MRI slices across these three views and categories. Our findings unequivocally demonstrate that the 'select slices' approach surpasses the use of entire slices in MRI images for AD classification. Specifically, our method elevates machine learning accuracy, with the coronal view showcasing exceptional performance. This methodology is a game-changer in improving the accuracy of machine learning models for AD classification, with results closely mirroring those of medical experts, the gold standard for AD diagnosis. Moreover, we observed that LeNet models hold great promise as effective tools for AD classification. (shrink)

As our epistemic ambitions grow, the common and scientific endeavours are becoming increasingly dependent on Machine Learning (ML). The field rests on a single experimental paradigm, which consists of splitting the available data into a training and testing set and using the latter to measure how well the trained ML model generalises to unseen samples. If the model reaches acceptable accuracy, an a posteriori contract comes into effect between humans and the model, supposedly allowing its deployment to target (...) environments. Yet the latter part of the contract depends on human inductive predictions or generalisations, which infer a uniformity between the trained ML model and the targets. The paper asks how we justify the contract between human and machine learning. It is argued that the justification becomes a pressing issue when we use ML to reach ‘elsewheres’ in space and time or deploy ML models in non-benign environments. The paper argues that the only viable version of the contract can be based on optimality (instead of on reliability which cannot be justified without circularity) and aligns this position with Schurz’s optimality justification. It is shown that when dealing with inaccessible/unstable ground-truths (‘elsewheres’ and non-benign targets), the optimality justification undergoes a slight change, which should reflect critically on our epistemic ambitions. Therefore, the study of ML robustness should involve not only heuristics that lead to acceptable accuracies on testing sets. The justification of human inductive predictions or generalisations about the uniformity between ML models and targets should be included as well. Without it, the assumptions about inductive risk minimisation in ML are not addressed in full. (shrink)

Phishing sites which expects to take the victims confidential data by diverting them to surf a fake website page that resembles a honest to goodness one is another type of criminal acts through the internet and its one of the especially concerns toward numerous areas including e-managing an account and retailing. Phishing site detection is truly an unpredictable and element issue including numerous components and criteria that are not stable. On account of the last and in addition ambiguities in arranging (...) sites because of the intelligent procedures programmers are utilizing, some keen proactive strategies can be helpful and powerful tools can be utilized, for example, fuzzy, neural system and data mining methods can be a successful mechanism in distinguishing phishing sites. We applied Random Forest (RF), one of the different types of machine learning based algorithms used for detection of Phishing websites. Finally we measured and compared the performance of the classifier in terms of accuracy. (shrink)

Financial forecasting plays a crucial role in guiding investment decisions, risk management, and strategic planning. Traditional forecasting methods, such as time series analysis and regression models, often struggle to capture the complexities and non-linear dynamics of financial markets. Machine learning (ML) has emerged as a powerful tool in financial forecasting due to its ability to process vast datasets, identify patterns, and enhance predictive accuracy. This paper explores various ML techniques, including neural networks, ensemble methods, and reinforcement learning, (...) applied to financial forecasting. It examines data acquisition, preprocessing, and feature engineering, along with case studies on stock price prediction, forex exchange rate forecasting, and credit risk assessment. Performance metrics such as Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) are analyzed to evaluate model effectiveness. Despite its advantages, ML in finance faces challenges like data quality, overfitting, and the need for interpretability. Ethical concerns, including bias and transparency, are also addressed. The paper highlights future directions, such as explainable AI, quantum computing, and big data applications. Ultimately, ML has the potential to transform financial forecasting, but its responsible implementation requires addressing regulatory, ethical, and technical challenges. (shrink)

Electrocardiogram (ECG) signal analysis is a critical task in healthcare for diagnosing cardiovascular conditions such as arrhythmias, heart attacks, and other heart-related diseases. With the growth of Internet of Things (IoT) networks, real-time ECG monitoring has become possible through wearable devices and sensors, providing continuous patient health monitoring. However, real-time ECG signal analysis in IoT environments poses several challenges, including data latency, limited computational power of IoT devices, and energy constraints. This paper proposes a framework for Optimized Machine (...) class='Hi'>Learning Algorithms designed to analyze ECG signals in real time within IoT networks. The proposed system leverages lightweight machine learning models, including support vector machines (SVM) and convolutional neural networks (CNNs), optimized to run efficiently on low-power IoT devices while maintaining high accuracy. The system addresses the computational limitations of IoT devices by employing edge computing techniques that distribute the processing load between IoT devices and edge servers. Additionally, data compression and feature extraction techniques are applied to reduce the size of the data transmitted over the network, thereby minimizing latency and bandwidth usage. This paper reviews the current advancements in real-time ECG analysis, explores the challenges posed by IoT environments, and presents the optimized machine learning algorithms that enhance real-time monitoring of heart health. The system is evaluated for its performance in terms of accuracy, energy efficiency, and data transmission speed, showing promising results in improving real-time ECG signal analysis in resource-constrained IoT networks. (shrink)

This paper provides an analysis of the way in which two foundational principles of medical ethics–the trusted doctor and patient autonomy–can be undermined by the use of machine learning (ML) algorithms and addresses its legal significance. This paper can be a guide to both health care providers and other stakeholders about how to anticipate and in some cases mitigate ethical conflicts caused by the use of ML in healthcare. It can also be read as a road map as (...) to what needs to be done to achieve an acceptable level of explainability in an ML algorithm when it is used in a healthcare context. (shrink)

This article assesses how autonomy and machine learning impact the existential risk of nuclear war. It situates the problem of cyber security, which proceeds by stealth, within the larger context of nuclear deterrence, which is effective when it functions with transparency and credibility. Cyber vulnerabilities poses new weaknesses to the strategic stability provided by nuclear deterrence. This article offers best practices for the use of computer and information technologies integrated into nuclear weapons systems. Focusing on nuclear command and (...) control, avoiding autonomy and machine learning is recommended as one means to reduce the existential risk of unintended nuclear conflict. (shrink)

Whether it would take one decade or several centuries, many agree that it is possible to create a *superintelligence*---an artificial intelligence with a godlike ability to achieve its goals. And many who have reflected carefully on this fact agree that our best hope for a "friendly" superintelligence is to design it to *learn* values like ours, since our values are too complex to program or hardwire explicitly. But the value learning approach to AI safety faces three particularly philosophical puzzles: (...) first, it is unclear how any intelligent system could learn its final values, since to judge one supposedly "final" value against another seems to require a further background standard for judging. Second, it is unclear how to determine the content of a system's values based on its physical or computational structure. Finally, there is the distinctly ethical question of which values we should best aim for the system to learn. I outline a potential answer to these interrelated puzzles, centering on a "miktotelic" proposal for blending a complex, learnable final value out of many simpler ones. (shrink)

Objectives: Machine learning (ML) has the potential to facilitate “continual learning” in medicine, in which an ML system continues to evolve in response to exposure to new data over time, even after being deployed in a clinical setting. In this article, we provide a tutorial on the range of ethical issues raised by the use of such “adaptive” ML systems in medicine that have, thus far, been neglected in the literature. -/- Target audience: The target audiences for (...) this tutorial are the developers of ML AI systems, healthcare regulators, the broader medical informatics community, and practicing clinicians. -/- Scope: Discussions of adaptive ML systems to date have overlooked the distinction between 2 sorts of variance that such systems may exhibit—diachronic evolution (change over time) and synchronic variation (difference between cotemporaneous instantiations of the algorithm at different sites)—and underestimated the significance of the latter. We highlight the challenges that diachronic evolution and synchronic variation present for the quality of patient care, informed consent, and equity, and discuss the complex ethical trade-offs involved in the design of such systems. (shrink)

The use of machine learning to medical image classification has seen significant development and implementation in the last several years. Computers can learn to identify patterns, make predictions, and use data to inform their judgements; this capability is known as machine learning, a branch of Artificial intelligence (AI). Classifying images according to their contents allows us to do things like identify the type of sickness, organ, or tissue depicted. Medical picture classification and interpretation using machine (...) learning algorithms has greatly improved the speed and accuracy of diagnosis and treatment. Machine learning algorithms can aid radiologists and doctors in diagnosing patients using medical pictures from X-rays, positron emission tomography (PET), computed tomography (CT), magnetic resonance imaging (MRI), and other scans. (shrink)

As machine learning (ML) models become increasingly integrated into mission-critical applications and production systems, the need for robust and scalable MLOps (Machine Learning Operations) practices has grown significantly. This paper explores key strategies and best practices for building scalable MLOps pipelines to optimize the deployment and operation of machine learning models at an enterprise scale. It delves into the importance of automating the end-to-end lifecycle of ML models, from data ingestion and model training to (...) testing, deployment, and monitoring. Approaches for implementing continuous integration and continuous deployment (CI/CD) pipelines tailored for ML workflows are discussed, enabling efficient and repeatable model updates and deployments. The paper emphasizes the criticality of implementing comprehensive monitoring and observability mechanisms to track model performance, detect drift, and ensure the reliability and trustworthiness of deployed models. The paper also addresses the challenges of managing model versioning and governance at scale, including techniques for maintaining a centralized model registry, enforcing access controls, and ensuring compliance with regulatory requirements. The paper aims to provide a comprehensive guide for organizations seeking to establish scalable and robust MLOps practices, enabling them to unlock the full potential of machine learning while mitigating risks and ensuring responsible AI deployment. (shrink)

Agriculture contributes a significant amount to the economy of India due to the dependence on humanbeings for their survival. The main obstacle to food security is population expansion leading to rising demand for food. Farmers must produce more on the same land to boost the supply. Through crop yield prediction, technology can assist farmers in producing more. This paper’s primary goal is to predict crop yield utilizing the variables of rainfall, crop, meteorological conditions, area, production, and yield that have posed (...) a serious threat to the long-term viability of agriculture. Crop yield prediction is a decision-support tool that uses machine learning and deep learning that can be used to make decisions about which crops to produce and what to do in the crop’s growing season. It can decide which crops to produce and what to do in the crop’s growing season. Regardless of the distracting environment, machine learning and deep learning algorithms are utilized in crop selection to reduce agricultural yield output losses. To estimate the agricultural yield, machine learning techniques: decision tree, random forest, and XGBoost regression; deep learning techniques- convolutional neural network and long-short term memory network have been used. Accuracy, root mean square error, mean square error, mean absolute error, standard deviation, and losses are compared. Other machine learning and deep learning methods fall short compared to the random forest and convolutional neural network. The random forest has a maximum accuracy of 98.96%, mean absolute error of 1.97, root mean square error of 2.45, and standard deviation of 1.23. The convolutional neural network has been evaluated with a minimum loss of 0.00060. Consequently, a model is developed that, compared to other algorithms, predicts the yield quite well. The findings are then analyzed using the root mean square error metric to understand better how the model’s errors compare to those of the other methods. (shrink)

Machine learning (ML) models have become integral to decision-making processes across various sectors, including healthcare, finance, and criminal justice. However, these models often inherit and even amplify biases present in training data, leading to unfair outcomes for certain demographic groups. This paper critically examines the ethical implications of bias and fairness in ML models, exploring the sources of bias, its impact on marginalized communities, and the ethical challenges it poses. We review recent literature to identify common biases in (...) ML systems, such as racial, gender, and socioeconomic biases, and discuss the consequences of these biases in realworld applications. Furthermore, we evaluate existing fairness metrics and mitigation strategies, highlighting their strengths and limitations. The paper also discusses the role of transparency, accountability, and regulation in addressing these ethical concerns. Through this examination, we aim to provide a comprehensive understanding of the ethical dimensions of bias and fairness in ML models and propose pathways toward more equitable AI systems. (shrink)

The proliferation of the Internet of Things (IoT) has transformed various industries by enabling smart environments and improving operational efficiencies. However, this expansion has introduced numerous security vulnerabilities, making IoT systems prime targets for cyberattacks. This paper proposes a machine learning-based intrusion detection framework tailored to the unique characteristics of IoT environments. The framework leverages feature engineering, advanced machine learning algorithms, and real-time anomaly detection to identify and mitigate security threats effectively. Experimental results demonstrate the efficacy (...) of the proposed approach in detecting diverse IoT-specific attacks, including denial-of-service (DoS), man-in-the-middle (MITM), and malware-based attacks. The Internet of Things (IoT) has revolutionized modern living by interconnecting devices and enabling seamless communication. However, the increasing reliance on IoT systems has exposed significant vulnerabilities, making them a prime target for security attacks. This paper proposes a machine learning-based intrusion detection framework to detect and mitigate security attacks in IoT environments. The framework integrates diverse machine learning algorithms to identify abnormal behavior and potential threats. Through comprehensive experiments and evaluations, this research demonstrates the efficacy of the proposed framework in terms of accuracy, scalability, and robustness. (shrink)

As more people utilise online banking services, the large losses that banks and other financial institutions sustained because of new bank account (NBA) fraud are concerning. Machine learning (ML) models have faced significant challenges because to the intrinsic skewness and rarity of NBA fraud cases. This occurs when the number of non-fraud instances exceeds the number of fraud instances, causing the ML models to miss and mistakenly regard fraud as non-fraud instances. Customers' confidence and trust may be damaged (...) by such mistakes. Existing research addresses the skewness of fraud datasets by considering fraud patterns rather than possible losses of NBA fraud risk characteristics. This study suggests NBA fraud detection in the framework of value-at-risk, a risk metric that views fraud cases as the worst-case situation. Value-at-risk models risk features as a skewed tail distribution and estimates possible losses of such attributes using historical simulation. ML was used to classify the risk-return characteristics derived from value-at-risk on the bank account fraud (BAF) dataset. The value-at-risk assigns weight to the skewed NBA fraud cases by managing the fraud skewness with an adjusted threshold probability range. The effectiveness of the fraud detection algorithm was assessed using a unique detection rate (DT) metric that takes risk fraud characteristics into account. A K-nearest neighbour with a true positive (TP) rate of 0.95 and a DT rate of 0.9406 is used to create an enhanced fraud detection model. Value-at-risk offers a clever way to create data-driven standards for fraud risk management within a reasonable loss tolerance in the banking industry. (shrink)

What can contemporary machine learning (ML) models do? Given the proliferation of ML models in society, answering this question matters to a variety of stakeholders, both public and private. The evaluation of models' capabilities is rapidly emerging as a key subfield of modern ML, buoyed by regulatory attention and government grants. Despite this, the notion of an ML model possessing a capability has not been interrogated: what are we saying when we say that a model is able to (...) do something? And what sorts of evidence bear upon this question? -/- In this paper, we aim to answer these questions, using the capabilities of large language models (LLMs) as a running example. Drawing on the large philosophical literature on abilities, we develop an account of ML models' capabilities which can be usefully applied to the nascent science of model evaluation. Our core proposal is a conditional analysis of model abilities (CAMA): crudely, a machine learning model has a capability to X just when it would reliably succeed at doing X if it 'tried'. The main contribution of the paper is making this proposal precise in the context of ML, resulting in an operationalisation of CAMA applicable to LLMs. We then put CAMA to work, showing that it can help make sense of various features of ML model evaluation practice, as well as suggest procedures for performing fair inter-model comparisons. (shrink)

: The integration of Machine Learning (ML) in Real-Time Biomedical Signal Processing has unlocked new possibilities in the field of telemedicine, especially when combined with the high-speed, low-latency capabilities of 5G networks. As telemedicine grows in importance, particularly in remote and underserved areas, real-time processing of biomedical signals such as ECG, EEG, and EMG is essential for accurate diagnosis and continuous monitoring of patients. Machine learning algorithms can be used to analyze large volumes of biomedical data, (...) enabling faster and more precise detection of anomalies. This paper proposes a novel system for machine learning-based real-time biomedical signal processing that leverages the capabilities of 5G networks to enhance the transmission, processing, and analysis of critical medical data in telemedicine applications. The system integrates convolutional neural networks (CNNs) for signal classification, anomaly detection, and predictive analysis, ensuring that patients receive timely and accurate medical feedback. Additionally, the 5G network’s low latency and high bandwidth provide seamless data transmission, improving remote diagnostics and enabling high-quality teleconsultations. This paper evaluates the current challenges in real-time biomedical signal processing in telemedicine, discusses the potential of machine learning and 5G networks, and presents an innovative solution for improving healthcare delivery through this integrated approach. (shrink)

A novel advantage of the use of machine learning (ML) systems in medicine is their potential to continue learning from new data after implementation in clinical practice. To date, considerations of the ethical questions raised by the design and use of adaptive machine learning systems in medicine have, for the most part, been confined to discussion of the so-called “update problem,” which concerns how regulators should approach systems whose performance and parameters continue to change even (...) after they have received regulatory approval. In this paper, we draw attention to a prior ethical question: whether the continuous learning that will occur in such systems after their initial deployment should be classified, and regulated, as medical research? We argue that there is a strong prima facie case that the use of continuous learning in medical ML systems should be categorized, and regulated, as research and that individuals whose treatment involves such systems should be treated as research subjects. (shrink)

Artificial intelligence technology that recognizes, learns, infers, and responds to external stimuli has recently attracted a lot of research interest. Information in a variety of domains by fusing big data, machine learning algorithms, and computing technologies. Nowadays, practically every industry uses artificial intelligence technology, and a large number of machine learning specialists are attempting to standardize and integrate different machine learning tools so that non-experts can use them with ease in their field. In order (...) to standardize the concepts of machine learning, the researchers are also investigating autonomous machine learning and ontology construction. In this paper, we present a problem solving process and categorize common steps in autonomous machine learning problem solving as tasks. We suggest a way to model self-learning machines using a workflow of machine learning tasks. Our proposed machine learning model based on task ontology, sets up a way to group UML activities by task. It will also create and grow machine learning models on its own using rules to change common parts and structures (how elements connect and work together). (shrink)

One of the main worries with machine learning model opacity is that we cannot know enough about how the model works to fully understand the decisions they make. But how much is model opacity really a problem? This chapter argues that the problem of machine learning model opacity is entangled with non-epistemic values. The chapter considers three different stages of the machine learning modeling process that corresponds to understanding phenomena: (i) model acceptance and linking (...) the model to the phenomenon, (ii) explanation, and (iii) attributions of understanding. At each of these stages, non-epistemic values can, in part, determine how much machine learning model opacity poses a problem. (shrink)

The advent of cloud computing has revolutionized how machine learning (ML) models are developed, trained, and deployed. By providing scalable, on-demand infrastructure, cloud platforms empower researchers, startups, and enterprises to leverage advanced ML capabilities without the burden of maintaining expensive hardware. This paper explores best practices and diverse use cases for implementing machine learning in the cloud, focusing on resource optimization, workflow automation, and model lifecycle management. Cloud-based machine learning offers several strategic benefits including (...) cost-efficiency, ease of access to high- performance computing (HPC), and the integration of managed services for data preprocessing, model training, deployment, and monitoring. Popular services such as Amazon SageMaker, Google Cloud Vertex AI, and Microsoft Azure ML provide comprehensive environments that simplify end-to-end ML development. However, challenges such as data privacy, vendor lock-in, and cost unpredictability remain persistent concerns. This paper reviews recent literature and analyzes real-world applications of cloud ML in industries like healthcare, finance, and retail. It outlines a research methodology centered around evaluating ML workflows across leading cloud platforms, followed by a discussion of key findings on performance, cost, and scalability. A structured workflow is proposed to guide practitioners in selecting appropriate tools and architectures. Furthermore, the paper identifies the primary advantages and drawbacks of cloud-based ML, concluding with recommendations for overcoming current limitations and future research directions. Use cases such as fraud detection, medical diagnostics, customer segmentation, and predictive maintenance demonstrate the transformative potential of cloud-based ML when implemented with best practices. By highlighting successful implementations and addressing operational trade-offs, this work serves as a practical guide for decision-makers and ML practitioners aiming to maximize the value of machine learning in the cloud. Through a comprehensive examination of tools, techniques, and real-world scenarios, it aims to contribute to more efficient, ethical, and scalable ML solutions. (shrink)

With the increasing demand for machine learning (ML) applications across various industries, the environmental impact of training large models has become a significant concern. Green AI emphasizes the development of machine learning models that are energy-efficient, requiring fewer computational resources while maintaining high performance. This paper explores how lightweight machine learning models, implemented with Python, can contribute to Green AI practices. We review several approaches for designing compact models, including model pruning, knowledge distillation, and (...) efficient architectures such as decision trees, linear models, and lightweight neural networks. By adopting these techniques, organizations can reduce the carbon footprint of AI systems without compromising accuracy. Through practical examples, we demonstrate how Python libraries and tools can facilitate the creation of lightweight models in an energy-efficient manner. (shrink)

Wine quality prediction is a significant task in the wine industry, as it helps producers and consumers determine the quality of a wine based on its chemical properties. Traditional methods of evaluating wine quality are subjective and time-consuming, relying on human tasters. However, with the advancement of machine learning (ML), it is now possible to predict wine quality in a more objective, scalable, and efficient manner. This paper explores various machine learning algorithms for predicting wine quality, (...) evaluates their performance, and demonstrates how these models can be applied to improve wine classification systems. (shrink)

Emotion recognition from speech is an important aspect of human-computer interaction (HCI) systems, allowing machines to better understand human emotions and respond accordingly. This paper explores the use of machine learning techniques to recognize emotions in speech signals. We leverage the librosa library for feature extraction from audio files and train multiple machine learning models, including Support Vector Machine (SVM), Random Forest (RF), and k-Nearest Neighbors (k-NN), to classify speech emotions. The aim is to create (...) an automated system capable of identifying emotions like happy, sad, angry, neutral, and surprised from speech audio. (shrink)

: In the realm of insurance, accurately predicting the charges or premiums that a policyholder will pay is a critical task. Traditional models may not fully capture the complexities involved due to the multifaceted nature of insurance data. This paper explores the use of machine learning (ML) techniques to predict insurance charges, providing a more data-driven and potentially more accurate method compared to conventional approaches. We will analyze various machine learning models, evaluate their performance, and discuss (...) their potential for use in insurance companies to enhance pricing accuracy and efficiency. (shrink)

Today e-commerce has had tremendous growth in the past years primarily due to changes in technology and customer’s buying behavior. One of the big shifts in the process has been the use of ML in advertising which has the capability to transform the marketing domain together with consumer interactions. This paper discusses the viability of using machine learning for designing realistic models of advertising to increase effectiveness of target and personalized advertising, as well as conversion rates in e-commerce. (...) Several techniques are explored in the study, such as supervised and unsupervised learning, recommender systems, and content optimization with natural language processing. By using case studies and experimental models, we discuss how and to what extent ML is beneficial in e-commerce advertising transformation. The results presented in this paper indicate that using machine learning in advertising has a potential of dramatically improving the customer experience while simultaneously increasing brand recognition and sales. (shrink)

With the increasing demand for machine learning (ML) applications across various industries, the environmental impact of training large models has become a significant concern. Green AI emphasizes the development of machine learning models that are energy-efficient, requiring fewer computational resources while maintaining high performance. This paper explores how lightweight machine learning models, implemented with Python, can contribute to Green AI practices. We review several approaches for designing compact models, including model pruning, knowledge distillation, and (...) efficient architectures such as decision trees, linear models, and lightweight neural networks. By adopting these techniques, organizations can reduce the carbon footprint of AI systems without compromising accuracy. Through practical examples, we demonstrate how Python libraries and tools can facilitate the creation of lightweight models in an energy-efficient manner. (shrink)

Coronary Heart Disease (CHD) is one of the leading causes of death nowadays. Prediction of the disease at an early stage is crucial for many health care providers to protect their patients and save lives and costly hospitalization resources. The use of machine learning in the prediction of serious disease events using routine medical records has been successful in recent years. In this paper, a comparative analysis of different machine learning techniques that can accurately predict the (...) occurrence of CHD events from clinical data was performed. Four machine learning classifiers, namely Logistic Regression, Support Vector Machine (SVM), K- Nearest Neighbor (KNN), and Multi-Layer Perceptron (MLP) Neural Networks were identified and applied to a dataset of 462 medical instances and 9 features as well as the class feature from the South African Heart Disease data retrieved from the KEEL repository. The dataset consists of 302 records of healthy patients and 160 records of patients who suffer from CHD. In order to handle the imbalanced classification problem, the K-means algorithm along with Synthetic Minority Oversampling TEchnique (SMOTE) was used in this study. The empirical results of applying the four machine learning classifiers on the oversampled dataset have been very promising. The results reported using different evaluation metrics showed that SVM has achieved the highest overall prediction performance. (shrink)