Abstract:On the basis of integrating the wavelet denoising, the theory of phase space reconstruction and LSSVM, a modeling and forecasting technique is put forward. First, the wavelet denoising is used to preprocess data, then the best embedding dimension and time delay of nonlinear deformation data are calculated with the method called “CC”, the phasespace is reconstructed as well. At last, the modeling prediction is carried out by LSSVM and also is compared with BP neural network. The results show that the prediction model of chaotic time series based on wavelet denoising and LSSVM is better.
Qin Yongkuan,Huang Shengxiang,and Zhao Qing. PREDICTION MODEL OF CHAOTIC TIME SERIES BASED ONWAVELET DE-NOISING AND LS-SVM AND ITS APPLICATION[J]. jgg, 2008, 28(6): 96-100.