A Multidisciplinary Approach to Understanding and Preventing Drowsy Driving: Environmental, Physiological, Behavioral, and Technological Perspectives

Abstract

 Drowsy driving is a serious global traffic hazard, with particularly high fatality rates in South Korea, exposing flaws in current prevention strategies. This paper examines five key areas to combat the issue: (1) real-time detection via machine learning, (2) environmental factors like PM2.5, (3) behavioral influences such as road monotony, (4) physiological effects of sleep deprivation, and (5) demographic and policy data. Machine learning enables personalized monitoring of eyelid closure, steering patterns, and breathing irregularities. Environmental and behavioral analyses identify external contributors, while sleep deprivation research highlights cognitive impairments, emphasizing the need for integrated health measures. Demographic trends and policy gaps reveal systemic weaknesses. By merging technology-based detection, public health interventions, and infrastructure reform, this study proposes a unified framework to reduce drowsy driving crashes. The findings call for multidisciplinary collaboration and advanced vehicle safety systems to address one of the most underestimated causes of preventable road fatalities.