Evaluation of Drivers' Driving Behavior in Heavy Traffic Situations from OBD-II Data

Abstract

The analysis and discussion of the onboard diagnostic data will help understand the driver's behavioral characteristics and develop a sustainable transportation system. The research content of this paper is to mine the driving behavior data through the vehicle preload equipment, analyze the factors affecting safe driving and establish a prediction model. This study collected data from 50 Taiwanese drivers while operating in heavy traffic. Understand the driver's behavioral characteristics through data analysis, such as calculating the times of the driver's emergency braking is based on the driving speed. From this result, the index of dangerous driving is defined. In addition, the dangerous driving index and other variables were analyzed, and it was found that there was a significant relationship between dangerous driving and vehicle mileage and maximum speed. According to the results, the drive speed increases the driving risk, the mileage reduces the risk probability, and the prediction accuracy is 78.9%. Complete data needs to be collected to evaluate complete driving behavior characteristics for developing sustainable transportation goals.