Safety Evaluation of Traffic Accident Scene Based on Artificial Neural Network

Traffic accident often induces traffic bottleneck and affects other vehicles driving. The lengthways region around accident scene becomes dangerous because of comprehensive traffic behaviors, such as lane changing, vehicle merging and vehicle following. In order to research the methods of management in traffic accident scene and avoid secondary accident, evaluation index system of safety in accident scene was established. Membership degree and dimensionless function were adapted to deal with quantitative and qualitative index. The three level BP neutral network model was developed to evaluate safety level in traffic accident scene. The results are shown that the evaluation index is logical and the conclusion is objective.