Detection Model on Fatigue Driving Behaviors Based on the Running State of Freight Vehicles

Fatigue driving is one of the main causes of truck accidents. Existing fatigue driving studies are mostly based on the vehicle running data or simulation data, which cause defects in the validity and reliability of the model. The paper extracts the sample data under different fatigue levels of drivers with naturalistic driving data of vehicle and drivers’ facial video. Based on that, indicators of vehicle running states are selected. The BP neural network is used to establish the detection model of fatigue driving behaviors, considering the influence of the number of model training samples and other parameters on the accuracy of fatigue driving behavior detection. The status data of 50 freight vehicles is used to test the detection model. Results show that the accuracy of the model can reach more than 80%. The model provides a new scheme for detecting fatigue driving behavior and a theoretical basis for fatigue warning.