Journal of System Simulation ›› 2021, Vol. 33 ›› Issue (1): 118-126.doi: 10.16182/j.issn1004731x.joss.20-0033

Previous Articles     Next Articles

Safety Evaluation and Risk Level Prediction of Driving Behavior Considering Multi-factors Influence

An Yu, Jiao Pengpeng, Bai Zixiu   

  1. Beijing Advanced Innovation Center for Future Urban Design, Beijing University of Civil Engineering and Architecture, Beijing 100044, China
  • Received:2020-01-10 Revised:2020-04-17 Published:2021-01-18

Abstract: In order to study the influence of multi-factors of human-vehicle-road on driving behavior and vehicle safety status in road traffic system, a simulated driving comparison test of six scenarios combined by multiple factors is designed. Driving simulator, physiography and eye tracker are used to collect 19 indicators related to driving behavior respectively. The differences of sample data are compared by variance analysis. The nonlinear SVM(support vector machine) is used to classify and predict the sample data. The driving behavior risk level prediction model is established, and the validity of the model is verified by the experimental data. The results show that the prediction accuracy of the model reaches 93.94%. The established risk level prediction model can effectively judge the status of the driver and the vehicle.

Key words: risk prediction, support vector machine, driving behavior, traffic safety, simulated driving

CLC Number: