期刊文献+

小波支持向量机 被引量:13

WAVELET SUPPORT VECTOR MACHINES
原文传递
导出
摘要 在研究支持向量机(SVM)核方法和小波框架理论的基础上,提出了一种称为小波支持向量机(WaveletSupport Vector Machines,WSVM)的新的机器学习构造方法.该方法引入小波基函数构造SVM的核函数,得到了一种新的SVM模型,然后提出了此模型的结构设计和实现算法,最后给出了几种常用的小波核函数,并给出了理论证明.通过仿真实验,把该方法与小波神经网络、高斯核SVM相比较,得到了较好的实验结果,从而验证了该方法的正确性和有效性. Based on the Kernel method of Support Vector Machines (SVM) and wavelet frame, a new method so-called Wavelet Support Vector Machines (WSVM) is proposed. A wavelet basis is introduced to construct kernel function of SVM. Furthermore, an algorithm for constructing and training the WSVM is presented. Finally, several common wavelet kernel functions are proposed and proved. Simulation examples are also given to illustrate the effectiveness of the method.
出处 《模式识别与人工智能》 EI CSCD 北大核心 2004年第2期167-172,共6页 Pattern Recognition and Artificial Intelligence
关键词 小波 支持向量机 核函数 框架理论 再生核希尔伯特空间 Wavelet Support Vector Machines Kemet Function Frame Theory Reproducing Kernet Hilbert Space
  • 相关文献

参考文献13

  • 1Zhang Q. Using Wavelet Network in Nonparametric Estimation.IEEE Trans on Neural Networks, 1997, 8(2) : 227 - 236.
  • 2Zhang Q, Benveniste A. Wavelet Network. IEEE Trans on Neural Networks, 1992, 3(9) : 889-898.
  • 3Zhang J, Walter G G, et al. Wavelet Neural Networks for Func-tion Learning. IEEE Trans on Neural Networks, 1995, 43 ( 6 ) :1485- 1497.
  • 4Qian W, Clarke I P. Wavelet-Based Neural Network with Fuzzy-Logic Adaptivity for Nuclear Image Restoration. Proc of the IEEE,1996, 84(10): 1458- 1473.
  • 5Bakshi B R, Stephanopoulos G. Wave-Net: A Multiresolution Hierarchical Neural Network with Localized Learning. IEEE Trans on Neural Networks, 1993, 39(1): 57-81.
  • 6Kreinocich V, Sirisaengtaksin O, Cabrera S. Wavelet Neural Networks Are Asymptotically Optimal Approximators for Functions of One Variable. Proc of the IEEE, 1994, 32(6) : 299- 304.
  • 7Vapnik V N. The Nature of Statistical Learning Theory. New York: Springer, 1995.
  • 8Millet-Roig J, Ventura-Galiano R, Chorro-Gasco F J, Cebrian A.Support Vector Machine for Arrhythmia Discrimination with Wavelet Transform-Based Feature Selection. Computers in Cardiology, 2000, 27( 1 ) : 407 - 410.
  • 9Strauss D, Steidl G, Jung J. Arrhythmia Detection Using Signal-Adapted Wavelet Preprocessing for Support Vector Machines.Computers in Cardiology, 2001, 28(2) : 497 - 500.
  • 10Ralotomamenjy A, Canu S. Learning, Frame, Reproducing Kernel and Regularization. Technical Report, TR2002- 01, Perception, Systems et Information, INSA de Rouen, St Etienne du Rouray, France, 2002.

同被引文献179

引证文献13

二级引证文献110

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部