Abstract:

In the reconstructed phase space, based on the Karhunen-Lo`eve transformation (KLT), the new local linear prediction method is proposed to predict chaotic time series. A noise-free chaotic time series and a noise addedchaotic time series are analyzed. The simulation results show that the KLT-based local linear prediction method can effectively make one-step and multi-step prediction for chaotic time series, and the one-step and multi-step prediction accuracies of the KLT-based local linear prediction method are superior to that of the traditional local linear prediction.