METHODS OF DRIVER FATIGUE CONTROL USING MACHINE LEARNING TECHNOLOGIES

The article discusses the methods of developing an intelligent system for monitoring driver fatigue using machine learning technologies. Driver fatigue is one of the leading causes of traffic accidents, especially on long routes and during night shifts. The proposed model based on the eye proportion coefficient (EAR) and a classifier using the support vector machine (SVM) method provides effective detection of blinks and other signs of fatigue in real time. Special attention is paid to the stability of the model to changes in lighting conditions and head orientation, which increases the reliability of the system in difficult operating conditions. As a result of testing the proposed system, high accuracy rates were obtained, which makes it suitable for use in intelligent transport systems.