哈尔滨工业大学学报（英文版）2008，Vol.15Issue(2)：248-254,7.
Reproducing wavelet kernel method in nonlinear system identification
Reproducing wavelet kernel method in nonlinear system identification
摘要
Abstract
By combining the wavelet decomposition with kernel method, a practical approach of universal multi-scale wavelet kernels constructed in reproducing kernel Hilbert space (RKHS) is discussed, and an identifica-tion scheme using wavelet support vector machines ( WSVM ) estimator is proposed for nonlinear dynamic sys-tems. The good approximating properties of wavelet kernel function enhance the generalization ability of the pro-posed method, and the comparison of some numerical experimental results between the novel approach and some existing methods is encouraging.关键词
wavelet kernels / support vector machine ( SVM ) / reproducing kernel Hilbert space (RKHS) /nonlinear system identificationKey words
wavelet kernels / support vector machine ( SVM ) / reproducing kernel Hilbert space (RKHS) /nonlinear system identification分类
信息技术与安全科学引用本文复制引用
WEN Xiang-jun,XU Xiao-ming,CAI Yun-ze..Reproducing wavelet kernel method in nonlinear system identification[J].哈尔滨工业大学学报（英文版）,2008,15(2):248-254,7.基金项目
Sponsored by the National 973 Key Fundamental Research Project of China (Grant No. 2002CB312200). （Grant No. 2002CB312200）
