计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (12): 222-225.DOI: 10.3778/j.issn.1002-8331.2009.12.071

• 工程与应用 • 上一篇    下一篇

最小二乘小波支持向量机的DNA序列分类方法

冼广铭1,曾碧卿1,冼广淋2   

  1. 1.华南师范大学 南海校区 计算机工程系,广东 佛山 528225
    2.广东轻工职业技术学院 计算机系,广州 510300
  • 收稿日期:2008-03-07 修回日期:2008-07-14 出版日期:2009-04-21 发布日期:2009-04-21
  • 通讯作者: 冼广铭

DNA classification based on Least Square Wavelet Support Vector Machine

XIAN Guang-ming1,ZENG Bi-qing1,XIAN Guang-lin2   

  1. 1.Computer Engineering Department of Nanhai Campus,South China Normal University,Foshan,Guangdong 528225,China
    2.Computer Engineering Department of Guangdong Industry Technical College,Guangzhou 510300,China
  • Received:2008-03-07 Revised:2008-07-14 Online:2009-04-21 Published:2009-04-21
  • Contact: XIAN Guang-ming

摘要: 目前使用的已有SVM核函数,在分类中不能逼近某一L2R)(平方可积空间)子空间上的任意分类界面。针对上述问题,在支持向量机的核函数方法和小波框架理论的基础上,提出了LS-WSVM结构模型。实验结果表明,和标准的SVM和LS-SVM比较起来,在同等条件下,LS-WSVM在分类方面具有优良的特征提取性能。

关键词: 支持向量机, 核函数, 最小二乘小波支持向量机, 分类

Abstract: SVM kernel function used at present can not approach to any classification boundary in sub-space of a square integrable space L2R).Aiming at the problem above,based on conditions of the support vector kernel function and wavelet frame theory,authors propose the construction model of Least Square Wavelet Support Vector Machine(LS-WSVM).Compared with standard SVM and LS-SVM under the same conditions,experimental results show that LS-WSVM has more excellent performance of feature abstraction in classification.

Key words: Support Vector Machine(SVM), kernel function, Least Square Wavelet Support Vector Machine(LS-WSVM), classification