International Journal of Scientific Research and Engineering Development

Road traffic accidents remain one of the leading causes of injuries and fatalities worldwide, and a significant portion of these incidents are caused by abnormal driving behaviors such as aggressive acceleration, sudden braking, distracted driving, and fatigue. Recent advancements in machine learning and intelligent transportation systems provide effective solutions for monitoring and analyzing driver behavior in real time. This paper proposes a Smart Driving Abnormality Detection System using Machine Learning to identify unsafe driving patterns and enhance road safety. The system collects vehicle and driver-related data such as speed, acceleration, braking patterns, and steering behavior, which are then processed through data preprocessing and feature extraction techniques. Machine learning algorithms are trained to classify driving behavior into normal and abnormal categories. The proposed system aims to detect risky driving actions and generate alerts to assist drivers and monitoring systems. Experimental results demonstrate that machine learning models can effectively analyze driving data and improve the accuracy of abnormal behavior detection. Such intelligent driver monitoring systems can contribute significantly to reducing traffic accidents and supporting the development of advanced driver-assistance systems (ADAS) and smart transportation infrastructure.

Dr.S.Rajeswari, Kishore Kumar S, Jerome R, Kathiravan R,"Smart Driving Abnormality Detection System Using Machine Learning" International Journal of Scientific Research and Engineering Development, V9(2): Page(1867-1874) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.