The 20th and 21st joint COTA International Conference of Transportation Professionals (CICTP 2020-21)

Fatigue driving causes road traffic accidents, so it is of great significance to study fatigue driving and to prevent early warnings.Currently, there are a variety of fatigue driving detection methods, including driving behavior, physiological signals, and methods based on the PERCLOS algorithm,but these detection methods have various problems.BP neural network combined with fatigue driving to better overcome the shortcomings of traditional methods.The driving behavior parameters are presented in the driving state, and the BP neural network is used to perform in-depth analysis on the driver's driving behavior, and then fatigue recognition is performed.The BP neural network extracts the corresponding driving operation behavior parameters, taking the parameters as input and the fatigue degree as the output, thus establishing a fatigue driving real-time monitoring system based on neural network applied to the machine.The system predicts the occurrence of fatigue driving, thereby improving the accuracy of fatigue detection, reducing the incidence of traffic accidents, and achieving automatic detection of fatigue driving. Keywords: Fatigue driving; BP neural network; fatigue identification; real-time monitoring

CICTP