Advancement in driver drowsiness and alcohol detection system using internet of things and machine learning

Globally traffic accidents are influenced by factors such as drowsiness and alcohol consumption. Consequently, there has been a considerable focus on the development of detection systems as part of ongoing efforts to mitigate these risks. This review paper aims to offer a comprehensive analysis of various drowsiness and alcohol detection methods. The paper particularly emphasizes drowsiness and alcohol detection methods, including those centered on sensor-based approaches, physiological-based techniques, and visual analysis of the eye and mouth state. The aim is to evaluate their method, effectiveness and highlight recent advancements within this domain. Additionally, this review paper evaluates the research gaps of these detection methods, considering factors such as precision, sensitivity, specificity, and adaptability to different environmental conditions.