计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (26): 156-158.

• 数据库与信息处理 • 上一篇    下一篇

基于支持向量机的无监督聚类算法研究

朱程辉1,2,孙东卫2,丰 义2,吴德会3   

  1. 1.合肥工业大学 电气与自动化工程学院,合肥 230019
    2.新疆轻工职业技术学院,乌鲁木齐 830021
    3.九江学院 电子工程系,九江 332005
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-09-11 发布日期:2007-09-11
  • 通讯作者: 朱程辉

Study on algorithm of non-monitor clustering based on support vector machines

ZHU Cheng-hui1,2,SUN Dong-wei2,FENG Yi2,WU De-hui3   

  1. 1.School of Electrical and Automation Engineering,Hefei University of Technology,Hefei 230019,China
    2.Xinjiang Light Industrial of Professional Technology College,Urumchi 830021,China
    3.Institute of Electron Engineering,Jiujiang University,Jiujiang,Jiangxi 332005,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-09-11 Published:2007-09-11
  • Contact: ZHU Cheng-hui

摘要: 分析了支持向量机在解决无监督分类问题上的不足,提出一种基于支持向量机思想的最大间距的聚类新方法。实验结果表明,该算法能成功地解决很多非监督分类问题。

关键词: 支持向量机, 结构风险, 无监督学习, 聚类

Abstract: This paper analyzes the ability of Support Vector Machinex(SVM) in dealing with the unsupervised learning problem,and proposes a new method of clustering with maximal margin based on the idea of SVM.In the experiment aspects,the results shows that this algorithm can deal with the unsupervised learning problem successfully.

Key words: Support Vector Machine(SVM), structure risk, unsupervised learning, clustering