Application of least square support vector machine based on particle swarm optimization to chaotic time series prediction

Abstract

The prediction of chaotic time series is performed by least square support vector machine (LS-SVM) based on particle swarm optimization (PSO). The main objective of this approach is to increase the accuracy of the chaotic time series prediction. For the generation performance of LS-SVM depending on a good setting of its parameters, PSO is adopted to choose the global optimum parameters of LS-SVM automatically. The proposed model is applied to the three important chaotic time series including Mackey-Glass time series, Lorenz time series and Henon time series. The simulation results prove the feasibility and effectiveness of the method.