主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院

中国管理科学 ›› 2008, Vol. 16 ›› Issue (2): 140-144.

• 论文 • 上一篇    下一篇

半模糊超球支持向量机多类分类方法研究

郭雪松1, 袁治平2, 刘波1   

  1. 1. 西安交通大学公共政策与管理学院 陕西西安710049;
    2. 西安交通大学管理学院 陕西西安710049
  • 收稿日期:2007-03-27 修回日期:2008-03-31 出版日期:2008-04-30 发布日期:2008-04-30
  • 作者简介:郭雪松(1978- ),男(汉族),河北保定人,西安交通大学公共政策与管理学院讲师,研究方向:先进制造管理.
  • 基金资助:

    陕西省软科学项目(2006KR86);国家自然科学基金重点项目(70433003)

Study on Multi-class Classification Method Based on Semi-fuzzy Hypersphere Support Vector Machine

GUO Xue-song1, YUAN Zhi-ping2, LIU Bo1   

  1. 1. School of Public Policy and Administration, Xi'an Jiaotong University, Xi'an, 710049 China;
    2. School of Management, Xi'an Jiaotong University, Xi'an, 710049 China
  • Received:2007-03-27 Revised:2008-03-31 Online:2008-04-30 Published:2008-04-30

摘要: 针对支持向量机在大类别模式分类中存在的问题,提出了一种基于半模糊核聚类的超球支持向量机分类方法.该方法首先利用半模糊核聚类方法对样本进行预处理,完成边缘样本的选取,进而以所选样本为训练样本进行超球支持向量机训练,从而有效提高分类器的性能.实验表明,该方法比标准支持向量机多类分类方法具有更高的速度和精度.

关键词: 支持向量机, 多类分类, 半模糊核聚类, 超球

Abstract: Aiming at problems existing in the area of multi-class pattern recognition with large number of cata logs,a hypersphere support vector machine classification method based on semi-fuzzy kernel clustering is proposed.Samples are preprocessed with semi-fuzzy kernel clustering to ensure that the ones near boundaries are selected and then used to train hypersphere support vector machine so as to improve its performance efficiently.Some experimental results indicate that the new method yields higher precision and speed than classical support vector machine multi-class classification methods.

Key words: support vector machine, multi-class classification, semi-fuzzy kernel clustering, hypersp here

中图分类号: