Driver Drowsiness Prediction through Eye Movement Behavior: A Vision-Based Machine Learning Model

Driver fatigue is a major cause of road accidents worldwide, leading to severe injuries, fatalities, and economic losses. In this study, we present a real-time driver drowsiness detection system based on eye movement analysis, integrating machine learning algorithms with advanced eye-tracking technology. The system monitors blink rate, gaze duration, and pupil dilation to evaluate alertness levels. Using a combination of convolutional neural networks (CNN) for visual feature extraction and support vector machines (SVM) for classification, the proposed approach achieves high accuracy in detecting early signs of drowsiness. Experimental results demonstrate the system’s ability to provide timely alerts, potentially reducing accident risks and improving road safety.