• V. S Krishna Prasad
• Dr. S Saravanan

Driver drowsiness significantly contributes to road accidents, highlighting the need for intelligent monitoring systems. This review analyzes 20 peer-reviewed studies (2019–2025) covering behavioral, physiological, and vehicle-based detection methods. Emphasis is placed on AI-driven approaches, particularly deep learning models like CNNs, LSTMs, Vision Transformers, and MobileNet V2. Multimodal systems using EEG, facial landmarks, thermal imaging, and smartphone data are evaluated for accuracy, scalability, and practical use. Detection accuracy ranges from 73% to 99.94%, with EEG-based methods achieving 73–85% and camera-based deep learning systems reaching up to 99.94%, especially with YOLOv8 and Swin Transformers. The review highlights performance trade-offs, deployment challenges, and the need for cost-effective, energy-efficient, and generalizable solutions. It aims to inform future research toward more interpretable and commercially viable drowsiness detection systems.

Driver Drowsiness Detection, Fatigue Monitoring, Deep Learning, Multimodal Sensing, Intelligent Transportation Systems, Behavioral Analysis, Physiological Signals.

"Advances in Driver Drowsiness Detection Systems: A Comprehensive Review of AI-Based Approaches and Emerging Trends", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 8, page no.d519-d529, August-2025, Available :http://www.jetir.org/papers/JETIR2508361.pdf

"Advances in Driver Drowsiness Detection Systems: A Comprehensive Review of AI-Based Approaches and Emerging Trends", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 8, page no. ppd519-d529, August-2025, Available at : http://www.jetir.org/papers/JETIR2508361.pdf