互联网 qkzz.net
全刊杂志网:首页 > 女性 > 文章正文
刊社推荐

一种新的模糊支持向量机多分类算法


□ 刘太安 梁永全 薛 欣

  266510;3.泰山学院 数学与系统科学系, 山东 泰安 271021)

  摘 要:在模糊多分类问题中,由于训练样本在训练过程中所起的作用不同,对所有数据包括异常数据赋予一个隶属度。针对模糊支持向量机(fuzzy support vector machines,FSVM)的第一种形式,引入类中心的概念,结合一对多1aa(oneagainstall)组合分类方法,提出了一种基于一对多组合的模糊支持向量机多分类算法,并与1a1(oneagainstone)组合和1aa组合的分类算法比较。数值实验表明,该算法是有效的,有较高的分类准确率,有更好的泛化能力。

  关键词:支持向量机;模糊支持向量机;一对多组合;隶属函数;多分类算法

  中图分类号:TP391 文献标志码:A

   文章编号:1001-3695(2008)07-2041-02

  

  New multiclassification algorithm based on fuzzy support vector machines

  

  LIU Taian1,LIANG Yongquan2,XUE Xin3

  (1.Dept. of Information & Engineering, Shandong University of Science & Technology, Tai’an Shandong 271019, China;2.College of Information Science & Engineering, Shandong University of Science & Technology, Qingdao Shandong 266510, China;3.Dept. of Mathematics & System Science, Taishan University, Tai’an Shandong 271021, China)

  Abstract:In the fuzzy multiclassification problem,gave a degree of membership to all the data including abnormal data as the training samples played different affections in the training procession. Facing to the first form of fuzzy support vector machines,used the concept of the class center. Considered with the oneagainstall association assorting method,put out a new fuzzy support vector machines multiclassification model based on oneagainstall association,and compared with oneagainstone and oneagainstall association assorting method. The numerical test has improved that the algorithm is effective, and it has higher accurate rate of classification,also better ability of generalization.

......
很抱歉,暂无全文,若需要阅读全文或喜欢本刊物请联系《计算机应用研究》杂志社购买。
欢迎作者提供全文,请点击编辑
分享:
 

了解更多资讯,请关注“木兰百花园”
分享:
 
精彩图文


关键字
支持中国杂志产业发展,请购买、订阅纸质杂志,欢迎杂志社提供过刊、样刊及电子版。
关于我们 | 网站声明 | 刊社管理 | 网站地图 | 联系方式 | 中图分类法 | RSS 2.0订阅 | IP查询
全刊杂志赏析网 2017