Truck Driver Safety Tendency Classification under Natural Driving Conditions Based on Gaussian Mixture Model (GMM)

You are here: Homepage > Search

Truck Driver Safety Tendency Classification under Natural Driving Conditions Based on Gaussian Mixture Model (GMM)

Zhang, Xiang / Zhao, Lei / Wang, Jian / Wen, Changlei / Xu, Ting

This study examines the differences in driving behavior of truck drivers. Vehicle driving data of 39 truck drivers in the natural driving state was obtained through vehicle OBD equipment. The characteristics of engine speed, vehicle lateral acceleration, driving speed, and vehicle longitudinal acceleration were extracted. To eliminate the influence of the external environment on the data, such as road bumps and engine shake, the mean filtering method was used to smooth the acquired data. The Gaussian mixture model established a driver’s personal trait identification model, and truck drivers were divided into ordinary drivers, aggressive drivers and conservative drivers. One-way ANOVA was performed on the classification results, significant differences were found between the variables, and the difference was statistically significant. Results show that the driver’s personal trait identification method based on Gaussian mixture model can effectively identify the driver type.