首页 | 本学科首页   官方微博 | 高级检索  
     

改进的二叉树支持向量机多类分类算法研究
引用本文:刘健,刘忠,熊鹰. 改进的二叉树支持向量机多类分类算法研究[J]. 计算机工程与应用, 2010, 46(33): 117-120. DOI: 10.3778/j.issn.1002-8331.2010.33.033
作者姓名:刘健  刘忠  熊鹰
作者单位:1.海军工程大学 船舶与动力学院,武汉 430033 2.海军工程大学 电子工程学院,武汉 430033
基金项目:中国博士后科学基金资助项目,海军工程大学自然科学基金 
摘    要:为解决现有支持向量机多类分类算法的不可分区域问题及提高泛化能力,提出一种改进的基于二叉树结构的支持向量机多类分类算法。该算法基于帕累托原则,将类超球体半径分解成核心半径和最小半径,通过两者加权计算最终的类超球体决策半径,并以此半径大小为依据生成二叉树结构。该算法避免了测量所引入的误差,使得样本分布广散布小的类处于二叉树的上层节点,从而获得更大的划分空间。实验结果表明:该算法具有一定的适应能力,能更好地解决实际多类分类问题。

关 键 词:多类别  支持向量机  二叉树  帕累托原则
收稿时间:2010-02-25
修稿时间:2010-4-13 

Improved multi-category support vector machines based on binary tree
LIU Jian,LIU Zhong,XIONG Ying. Improved multi-category support vector machines based on binary tree[J]. Computer Engineering and Applications, 2010, 46(33): 117-120. DOI: 10.3778/j.issn.1002-8331.2010.33.033
Authors:LIU Jian  LIU Zhong  XIONG Ying
Affiliation:1.Naval Architecture & Power Engineering College,Naval University of Engineering,Wuhan 430033,China 2.Electrical Engineering College,Naval University of Engineering,Wuhan 430033,China
Abstract:To resolve the unclassifiable regions and to elevate generalization ability of multi-category support vector machines at present,an improved multi-category SVM based on Binary Tree(BT-SVM) is proposed.The improved algorithm defines the decision-radius which comes from the category-hypersphere-radius that is divided into kernel-radius and max-radius based on Pareto principle.The final BT's structure is created by the decision-radius that can make the category which has wide-distribution and small-scatter on the top of BT, therefore the measurement errors are avoided.Numerical experiments on standard dataset demonstrate that the improved BT-SVM can better deal with practical multi-category classification problems with more adaptive ability.
Keywords:multi-category  support vector machines  binary tree  Pareto principle
本文献已被 维普 万方数据 等数据库收录!
点击此处可从《计算机工程与应用》浏览原始摘要信息
点击此处可从《计算机工程与应用》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号