Traffic Flow Forecasting based on PCA and Wavelet Neural Network

Accurate short-term traffic flow forecasting has become a crucial step in the overall goal of better road network management. A combination approach based on Principal Component Analysis (PCA) and Wavelet Neural Network(WNN) is presented for short-term traffic flow forecasting. The historical data of the forecasted traffic volume and interrelated volumes have been processed by PCA first, and then the results of PCA form the input data for WNN. The proposed method is applied to predict the real traffic flow in Yanta cross, Xi´an city, China. The forecast results show that this proposed method is better than the typical Back-Propagation neural network (BP NN) method with the same data.