Comparative Analysis of Drowsiness Detection Using Deep Learning Techniques

Abstract

Driver drowsiness increases crash risk, resulting in significant road damage each year. Driver drowsiness and rash driving are the leading causes of road accidents, which result in the loss of valuable lives and deteriorate road traffic safety. Various drowsiness detection systems have been developed using various technologies, with an emphasis on the unique parameter of detecting the driver's drowsiness. Deep learning techniques are currently a hot research topic in detection systems. The purpose of this paper is to compare the detection of driver drowsiness using deep learning techniques such as artificial neural networks (ANN), convolution neural networks (CNN), and deep convolutional neural networks (DCNN). This will determine whether the person is drowsy based on their eye score. If the eyes are closed until the bench score, the red alert will be activated, along with an alarm sound. This will determine whether or not the person is drowsy based on their eye score. If the eyes are closed until the bench score, the red alert will be activated, along with an alarm sound. The eyes will be detected whether they are open, semi-closed, or closed, and an alert will be generated to help prevent any type of road accident. To prevent accidents and improve road safety, reliable and precise driver drowsiness systems are required.