Analysis of Spectrum and Prediction for Short-term Traffic Flow

In this paper, based on analysing spectrum of short-term traffic flow by FFT transformation in limited length, we make use of neutral network to forecast the direct data and every scales data which was decomposed and reconstructed by wavelet analysis. Comparing with two results, prediction of the composing data which has been decomposed and reconstructed by wavelet has better accuracy, it can prove that wavelet analysis has value for studying in prediction of short-term traffic flow.