Multivariate chaotic time series prediction based on PLSR and MKELM

Abstract

This paper presents a method based on partial least squares regression (PLSR) and multiple kernel extreme learning machine (MKLEM) for multivariate chaotic time series prediction. At first, singular spectrum analysis (SSA) is applied for the time series extraction of complex trends and eliminating the influence of noise. Then, partial least squares regression is used to capture the essential structure of the data and extract the compositions, in order to overcome the multicollinearity problem among time series and reduce the input dimension of neural networks. Finally, multiple kernel extreme learning machine is used to predict the time series. Multiple kernel extreme learning machine overcomes the problem that single extreme learning machine with kernels (KELM) doesn't present an effective generalization performance. Root mean square error (RMSE) is used to measure the performance of the proposed prediction model. The simulation experiment results based on Lorenz chaotic time series and Dalian monthly average temperature-rainfall time series demonstrate that the proposed model is effective for time series prediction, and the prediction accuracy is higher than other models.