Highway Tunnel Traffic Accidents Prediction Model Based on BP Neural Network

摘要

A prediction model of China's highway tunnel traffic accidents is established, on the basis of the characteristics of BP neural network, such as auto-study, auto-organization and auto-ability. Using the grey relational theory, major influencing factor index of the highway tunnel traffic accidents are chosen, and key technologies of the construction of BP neural network predictive are also discussed . Then, the model is trained and tested using the statistics data of China's highway tunnel traffic accident from 1995 to 2008 . The results show that the precision of this prediction model is high, so that it could be applied to forecasting highway tunnel traffic accidents.