基于二叉树的多类SVM在Web文本分类中的应用研究The Application of Multi-class SVM based Binary Tree in Web Text Categorization
古丽娜孜,孙铁利
摘要(Abstract):
针对现有多分类支持向量机算法所存在的训练时间长、判别速度慢等问题,提出了一种二叉树多类支持向量机算法,该算法能够有效减少支持向量的个数,从而减少训练时间.为了验证算法的有效性,将该算法分别同l-v-r算法和l-v-1算法进行了比较,实验结果表明,提出的算法是有效可行的.
关键词(KeyWords): Web文本分类;二叉树;多分类SVM
基金项目(Foundation): 吉林省科技发展规划项目(20090503);; 教育部科技发展中心项目(20090043110010)
作者(Author): 古丽娜孜,孙铁利
参考文献(References):
- [1]史忠植.知识发现[M].北京:清华大学出版社,2002.
- [2]Sungmoon C,Sang H O,Soo-Young L.Support vector machines with binary tree architecture for multi-class classification[J].Neural Information Processing Letters and Reviews,2004,2(3):47-51.
- [3]Vapnik V.Statistical learning theory[M].NewYork:Springer Verlag,1998.
- [4]Ulrich Krebel.Pairwise classification and support vector machines[M].In B.Schuolkopf,Burges C J C,Smola A J,editors,Advances in Kernal Methods:Support Vector Learning,Pages,MITPress,Cambrige,MA,1999,255-268.
- [5]John C Platt.Large Margin DAGs for Multiclass Classification Advances in Neural[M].Information Processing Systems 12S.A.Solla,T K Leen,MIT Press,2000,547-553
- [6]Schwenker F.Hierarchical Support Vector Machines for Multi-Class Pattern Recognition,Fourth International conference onKnowledge-Based Intelligent Engineering Systems&Allied Technologies[M].Brighton,UK,2000.
- [7]刘志刚,李德仁,秦前清,等.支持向量机在多类分类问题中的推广[J].计算机工程与应用,2004,40(7):10-13.
- [8]马笑潇,黄席褪,柴毅.基于SVM的二叉树多类分类算法及其在故障诊断中的应用[J].控制与决策,2003,18(3):272-276.