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.

Large Language Models (LLMs), like GPT and BERT, have significantly advanced Natural Language Processing (NLP), enabling high performance on complex tasks. However, their size and computational needs make LLMs unsuitable for deployment on resource-constrained devices, where efficiency, speed, and low power consumption are critical. Tiny Language Models (TLMs), also known as BabyLMs, offer compact alternatives by using advanced compression and optimization techniques to function effectively on devices such as smartphones, Internet of Things (IoT) systems, and embedded platforms. This paper provides a comprehensive survey of TLM architectures and methodologies, including key techniques such as knowledge distillation, quantization, and pruning. Additionally, it explores potential and emerging applications of TLMs in automation and control, covering areas such as edge computing, IoT, industrial automation, and healthcare. The survey discusses challenges unique to TLMs, such as trade-offs between model size and accuracy, limited generalization, and ethical considerations in deployment. Future research directions are also proposed, focusing on hybrid compression techniques, application-specific adaptations, and context-aware TLMs optimized for hardware-specific constraints. This paper aims to serve as a foundational resource for advancing TLMs capabilities across diverse real-world applications.

The integration of Tiny Machine Learning (TinyML) with Human Behavior Analysis (HBA) represents a significant advancement in the field of Artificial Intelligence (AI), enabling real-time, efficient, and privacy-preserving analysis on resource-constrained devices. This paper provides the first comprehensive survey exploring this integration, presenting a detailed overview of TinyML, including its definitions, key concepts and advantages. The survey proposes a systematic taxonomy of TinyML applications in HBA, categorizing state-of-the-art implementations based on their use cases and specific methodologies. Furthermore, the challenges and limitations of integrating TinyML in HBA are thoroughly discussed, including technical constraints, data quality issues, and ethical considerations. Finally, future research directions and open issues are outlined, emphasizing the potential advancements and emerging trends in this field. This survey serves as a foundational resource, guiding researchers and practitioners in harnessing the capabilities of TinyML to advance HBA.

Tiny Machine Learning (TinyML) has emerged as a transformative paradigm enabling machine learning inference directly on ultra-low-power microcontrollers and edge devices. As AI expands beyond cloud computing to resource-constrained environments, TinyML offers promising solutions for latency-sensitive, bandwidth-efficient, and privacy-preserving applications. This paper presents a Systematic review of state-of-the-art TinyML applications across three critical domains: healthcare, education, and transportation. By analyzing 136 peer-reviewed publications from 2020 to 2025, we identify key trends, representative use cases, and the enabling technologies that support domain-specific deployments. Our review evaluates software frameworks, hardware platforms, model optimization techniques (e.g., quantization, pruning, and neural architecture search), and real-world deployment challenges such as energy consumption, memory limitations, and explainability. We further synthesize the metrics used to assess TinyML systems and highlight open research questions. Unlike previous surveys, our domain-centric approach offers a deeper contextual analysis of how TinyML is being adapted to solve real-world problems across diverse sectors. We conclude by outlining future directions and practical insights to guide researchers and practitioners in designing scalable, resilient, and ethically grounded TinyML systems.

The application of tiny machine learning (TinyML) in human-computer interaction is revolutionizing gesture recognition technologies. However, there remains a significant gap in the literature regarding the effective recognition of complex scripts, such as Arabic, in real-time applications. This research aims to bridge this gap by leveraging TinyML for the accurate recognition of Arabic numbers and simple letters through gesture-based air handwriting. For the first time, we introduce a novel tiny deep learning (TinyDL) model that utilizes a lightweight convolutional neural network (CNN) architecture specifically designed to handle the intricacies of the Arabic script and adaptable for the TinyML domain. Despite the widespread use of CNNs in gesture recognition, our model stands out by achieving an exceptional accuracy rate of 97.5% in decoding 2D gesture inputs of Arabic numerals and letters. This high level of accuracy demonstrates the effectiveness of our TinyDL model in addressing the unique challenges posed by Arabic script recognition, thereby making it a user-friendly and accessible solution. Moreover, our research contributes to the advancement of TinyML applications in real-world gesture recognition apps, showcasing the potential of TinyML in transforming the interaction between humans and digital devices.

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.