The Application of BP Neural Network Principal Component Analysis in the Forecasting the Road Traffic Accident

Abstract

According to complexity and comprehensibility of factors which affect road traffic safety, we use the method of principal component analysis to refine new factors which are linearly independent, then we forecast road traffic accident according to principal component by BP neural network simulation, analyse the relationship between traffic accident evaluating index and the causes of traffic accident, including people, vehicles, road and environment. At last we applied the method to a case, from the simulated result we can infer that the method of BP neural network simulation principal component analysis is superior to multinomial fitting and BP neural network simulation in the efficiency and precision.