基于模糊支持向量机的文本分类  

Text categorization method based on fuzzy support vector machine

作　　者：包剑[1] 冀明[1] 冯军[1] 

机构地区：[1]辽宁工程技术大学职业技术学院,辽宁阜新123000

出　　处：《辽宁工程技术大学学报（自然科学版）》2010年第5期974-977,共4页Journal of Liaoning Technical University (Natural Science)

基　　金：辽宁省教育厅高等学校科学研究项目资助(202182054)

摘　　要：为了有效地利用信息技术发展而产生的海量信息,信息检索与数据挖掘得到了快速的发展,通过对传统支持向量机的特点分析,针对其在文本分类中的局限性,采用了一种基于二叉树的模糊支持向量机的多分类算法,通过实验证明该算法有更好的抗干扰能力和更好的分类效果。In order to effectively use information technology generates huge amounts of information,information search and data mining has been rapid development,of which text categorization technology is the field of information search and data mining research focus and core technology,in recent years has been widespread attention. On the characteristics of the traditional support vector machine analysis,for its limitations in the text classification using a binary tree based on fuzzy support vector machine multi-classification algorithm,experiments show that the algorithm has better anti-interference capability and better results of classification.

关 键 词：模糊支持向量机 文本分类 机器学习 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]