Algorithms Comparison in Drowsiness Detection

Abstract

Drowsy driving is a recognized leading cause of road accidents, resulting in a considerable number of fatalities and injuries. This paper presents a proposed system that leverages machine learning algorithms, specifically Convolutional Neural Network (CNN) and Support Vector Machine (SVM), to accurately detect the drowsy state of drivers by analyzing the diameter of their eyes and comparing the level of dilation or constriction. Drowsy driving poses a significant problem on roadways, as indicated by the National Highway Traffic Safety Administration's data, which reports approximately 100,000 police-reported collisions each year involving drowsy driving, leading to over 1,550 fatalities and 71,000 injuries. The proposed system demonstrates the potential to reduce accidents associated with drowsy driving. We conducted an evaluation and comparison of the effectiveness of CNN and SVM algorithms with the objective of identifying the optimal algorithm for drowsiness detection. Our algorithms were trained on a comprehensive dataset comprising images of drowsy and alert drivers, enabling real-time and accurate identification of the driver's state. Employing advanced image processing techniques, the proposed system analyzes changes in eye diameter associated with drowsiness. Its purpose is to promptly alert drivers, thus mitigating accidents caused by drowsy driving. We anticipate that this system will provide a reliable and cost-effective solution to the problem of drowsy driving, with potential benefits for both drivers and passengers. Further research and development efforts could facilitate its widespread adoption in the automotive industry. This paper underscores the significance of addressing drowsy driving and introduces a promising solution through the application of machine learning algorithms.