Abstract: Driver drowsiness is a major concern in road safety, leading to numerous accidents and fatalities worldwide. Consequently, the development of accurate and reliable drowsiness detection systems is critical to enhance road safety. Recently, various machine learning (ML) algorithms have shown great potential in detecting drowsiness using various physiological and behavioral signals. Several fatal and non fatal injuries can be prevented if the drowsy drivers are warned in time. According to many recent surveys, around 21% of road accidents take place due to the driver’s drowsiness.

Many of these collisions lead to loss of life, property or infrastructure; endangering not only the driver but also other individuals. The transport businesses that employ overnight driving have been seen to be at the highest risk. Driving during the night can lead to severe fatigue and drowsiness even when the driver is well-rested. As a result, many automobile industries have begun to take steps to implement driver drowsiness detection systems. Existing systems implemented by top car brands consist of the ECG machines holstered within the sides of the driver’s seat. However, these have proved to be uncomfortable. Various Machine learning and deep learning models can be used to detect fatigue and drowsiness and potentially reduce the dependency on physical devices used in ECG.

Keywords: Drowsiness detection, Classification, Machine Learning, Deep Learning.

PDF | DOI: 10.17148/IJARCCE.2023.12337

Open chat
Chat with IJARCCE