Wavelet Support Vector Machine With Universal Approximation and its Application

摘要：

Wavelet Support Vector Machines (WSVM) using the Mexican Hat wavelet kernel has been used to nonlinear system identification successfully, but its universal approximation property has never been proved in theory. Based on StoneWeierstrass Theorem, the universal approximation property of the WSVM to arbitrary functions on a compact set is proved with arbitrary accuracy. These simulations show the WSVM is very effective in nonlinear system identification, and can deduce noise of the system, so WSVM has great potential applications in the function estimation, nonlinear system identification, signal processing and control.

作者: Wenhui Chen Wanzhao Cui Changchun Zhu

作者单位: School of Electronics and Information Northwestern Polytechnical University, Xian 710072,China National Key Laboratory of Space Microwave Technology Xian Institute of Space Radio Technology, Xi School of Electronics and Information Engineering Xian Jiaotong University, Xian 710049, China

会议类型: 国际会议

会议名称: 2006年IEEE信息理论国际会议(Proceedings of 2006 IEEE Information Theory Workshop ITW06)

会议地点: 成都

会议语种:英文

页码: 360-364

在线出版日期: 2006-10-22（万方平台首次上网日期，不代表论文的发表时间）