Using LS-SVM Pattern Recognizer to Detect Change-Point in ARMA Process

Based on LS-SVM pattern recognizer, this paper develops an intelligent method for solving the problem of change-point detection, and the proposed model is applied to detect change-point of process mean-shift in auto-correlated time series process. In this research, LS-SVM algorithm and moving window method are used to detect the location of the mean shift signal, the LS-SVM pattern recognizer is designed and the performance of the recognizer is evaluated in terms of Accuracy Rate. Results of simulation experiment show that the proposed intelligent model is an effective method to detect change-point in ARMA data series.