Drowsy driving poses a significant challenge to road safety worldwide, contributing to thousands of accidents and fatalities annually. Despite advancements in driver drowsiness detection (DDD) systems, many existing methods face limitations such as intrusiveness and delayed reaction times. This research addresses these gaps by leveraging facial analysis and state-of-the-art machine learning techniques to develop a real-time, non-intrusive DDD system. A distinctive aspect of this research is its systematic assessment of various machine and deep learning algorithms across three pivotal public datasets, the NTHUDDD, YawDD, and UTA-RLDD, known for their widespread use in drowsiness detection studies. Our evaluation covered techniques including the K-Nearest Neighbors (KNNs), support vector machines (SVMs), convolutional neural networks (CNNs), and advanced computer vision (CV) models such as YOLOv5, YOLOv8, and Faster R-CNN. Notably, the KNNs classifier reported the highest accuracy of 98.89%, a precision of 99.27%, and an F1 score of 98.86% on the UTA-RLDD. Among the CV methods, YOLOv5 and YOLOv8 demonstrated exceptional performance, achieving 100% precision and recall with mAP@0.5 values of 99.5% on the UTA-RLDD. In contrast, Faster R-CNN showed an accuracy of 81.0% and a precision of 63.4% on the same dataset. These results demonstrate the potential of our system to significantly enhance road safety by providing proactive alerts in real time.

The early detection of fire and smoke is essential for mitigating human casualties, property damage, and environmental impact. Traditional sensor-based and vision-based detection systems frequently exhibit high false alarm rates, delayed response times, and limited adaptability in complex or dynamic environments. Recent advances in deep learning and computer vision have enabled more accurate, real-time detection through the automated analysis of flame and smoke patterns. This paper presents a comprehensive review of deep learning techniques for fire and smoke detection, with a particular focus on convolutional neural networks (CNNs), object detection frameworks such as YOLO and Faster R-CNN, and spatiotemporal models for video-based analysis. We examine the benefits of these approaches in terms of improved accuracy, robustness, and deployment feasibility on resource-constrained platforms. Furthermore, we discuss current limitations, including the scarcity and diversity of annotated datasets, susceptibility to false alarms, and challenges in generalization across varying scenarios. Finally, we outline promising research directions, including multimodal sensor fusion, lightweight edge AI implementations, and the development of explainable deep learning models. By synthesizing recent advancements and identifying persistent challenges, this review provides a structured foundation for the design of next-generation intelligent fire detection systems.

Human Behavior Analysis (HBA) has emerged as a critical interdisciplinary field, combining psychology, sociology, artificial intelligence, and data science to model, understand, and predict human behavior across diverse domains. This paper provides a comprehensive survey, addressing gaps in existing literature by exploring applications, techniques, challenges, and future directions. We begin by defining HBA, tracing its historical roots, and outlining core concepts such as behavioral patterns, cognitive processes, and emotional states. The survey then explores traditional and modern techniques, from manual observation to AI-driven methods such as deep learning, natural language processing, and computer vision. A key contribution is our extensive coverage of HBA applications in healthcare, marketing, education, workplace productivity, activity recognition, and criminal justice. For each domain, we provide detailed examples of how HBA enhances outcomes and decision-making. The survey also delves into data sources and methodologies used in HBA, such as sensor data, social media data, physiological signals, and multimodal analysis. We discuss major challenges such as data privacy, generalization, real-time processing, and scalability. Finally, we highlight emerging trends and future directions, including edge computing, Large Language Models, privacy-preserving techniques, and cross-disciplinary approaches. By offering a holistic review, this survey aims to guide future research and innovation in the evolving field of HBA.

The integration of Tiny Machine Learning (TinyML) with human biometric recognition constitutes a significant advancement in enabling secure, efficient, and real-time identity verification on resource-constrained embedded devices. This paper provides the first comprehensive survey exploring this integration, encompassing both physiological modalities, such as fingerprint, face, and iris recognition, and behavioral modalities, including gait, voice, and keystroke dynamics. The foundational principles of TinyML are introduced, alongside a discussion of key enabling techniques, such as quantization, pruning, and the design of lightweight neural network architectures. A structured taxonomy of biometric applications is proposed, organizing recent research into five principal domains: wearable devices, smart home and IoT security, healthcare monitoring, access control systems, and surveillance. In addition, the survey critically evaluates the limitations of current TinyML-based biometric implementations, highlighting challenges related to memory and computational constraints, inference latency, robustness under varying conditions, privacy preservation, and lack of standardization. Finally, prospective research directions are outlined, emphasizing advances in federated learning, Tiny AutoML, multimodal fusion, and neuromorphic computing. Collectively, this work provides a comprehensive reference to guide researchers and practitioners in the development of reliable, privacy-aware, and highly efficient edge-deployed biometric recognition systems.

Generative artificial intelligence and foundation models have changed machine learning by allowing systems to produce readable text, realistic images, and other multimodal content with little direct input from a user. Foundation models are large neural networks trained on very large and varied datasets, and they form the core of many current generative AI (GenAI) systems. Their rapid development has led to major advances in areas like natural language processing, computer vision, multimodal learning, and robotics. Examples include GPT, LLaMA, and diffusion-based architectures, such as models often used for image generation. Systems such as Stable Diffusion show this shift by illustrating how AI can interpret information, draw basic inferences, and produce new outputs using more than one type of data. This review surveys common foundation model architectures and examines what they can do in generative tasks. It reviews Transformer, diffusion, and multimodal architectures, focusing on methods that support scaling and transfer across domains. The paper also reviews key approaches to pretraining and fine-tuning, including self-supervised learning, instruction tuning, and parameter-efficient adaptation, which support these systems’ ability to generalize across tasks. In addition to the technical details, this review discusses how GenAI is being used for text generation, image synthesis, robotics, and biomedical research. The study also notes continuing challenges, such as the high computing and energy demands of large models, ethical concerns about data bias and misinformation, and worries about privacy, reliability, and responsible use of AI in real settings. This review brings together ideas about model design, training methods, and social implications to point future research toward GenAI systems that are efficient, easy to interpret, and reliable, while supporting scientific progress and ethical responsibility.