Adaptive LS-SVM with modified L-P Wavelet Kernel and Applications

摘要：

A novel admissible support vector (SV) kernel,namely modified L-P wavelet kernel function,is proposed based on theoretic analysis.The wavelet kernel can approximate arbitrary curve in quadratic continuous integral space,thus the generalization ability of the support vector machines (SVM) is enhanced.Based on the wavelet function and Adaptive Least Square Support Vector Machine (ALSSVM),The ALS-SVM with modified L-P Wavelet Kernel (ALS-MLPWSVM) is presented.The ALS-SVM can adjust the model to track the dynamics of the nonlinear time-varying system.Simulation results show some advantages of ALS-MLPWSVM over ALS-SVM on the modelling and generalization performance.

关键词： modified L-P wavelet support vector kernel function adaptive LS-SVM dynamic system identification

作者: Yong-zhong Xing Xiao-bei Wu Zhi-liang Xu

作者单位: Institute of Automation,Nanjing University of Science and Technology,Nanjing,210094 China

会议类型: 国际会议

会议名称: International Conference on Modelling,Identification and Control(模拟、鉴定、控制国际会议)

会议地点: 上海

会议语种:英文

在线出版日期: 2008-06-29（万方平台首次上网日期，不代表论文的发表时间）