A Short-term Traffic Flow Prediction Method Based on Wavelet Analysis and Neural Network

A short-term traffic flow predicting mode is discussed based on the wavelet analysis and neural network. First, the basis theory of Mallat wavelet and BP neural network are introduced in detail. Secondly, a short-term traffic flow predicting model is constructed combining with Mallat wavelet and BP neural network. Meanwhile, the evaluating criterion of the prediction model is given according to the features of traffic data. Thus, the error structure of the constructed forecasting model is analyzed. Finally, the effectiveness of the short-term traffic predicting model is verified by using Chengdu-Chongqing high-speed detection information.