基于类向心度的模糊支持向量机

J4 ›› 2014, Vol. 36 ›› Issue (08): 1623-1628.

• 论文 • 上一篇

基于类向心度的模糊支持向量机

许翠云，业宁

(南京林业大学信息科学技术学院，江苏南京 210037)

收稿日期:2012-09-13 修回日期:2013-01-21 出版日期:2014-08-25 发布日期:2014-08-25
基金资助:
国家973计划资助项目（2012CB114505）；国家杰出青年计划资助项目（31125008）；江苏省研究生创新基金资助项目（CXLX11_0525，CXZZ12_0527）；江苏省青蓝工程学术带头人；江苏省六大人才高峰(电子信息类)

A novel fuzzy support vector
machine based on the class centripetal degree

XU Cuiyun,YE Ning

(School of Information Technology,Nanjing Forestry University,Nanjing 210037,China)

Received:2012-09-13 Revised:2013-01-21 Online:2014-08-25 Published:2014-08-25

摘要/Abstract

摘要：

传统支持向量机(SVM)训练含有噪声或野值点的数据时，容易产生过拟合，而模糊支持向量机可以有效地处理这种问题。针对使用样本与类中心之间的距离关系来构建模糊支持向量机隶属度函数的不足，提出了一种基于类向心度的模糊支持向量机(CCDFSVM)。该方法不仅考虑到样本与类中心之间的关系，还考虑到类中各个样本之间的联系，并用类向心度来表示。将类向心度应用于模糊隶属度函数的设计，能够很好地将有效样本与噪声、野值点样本区分开来，而且可以通过向心度的大小，对混合度比较高的样本进行区分，从而达到提高分类精度的效果。实验结果表明，基于类向心度的模糊支持向量机其分类正确率比支持向量机高，在使用三种不同隶属度函数的FSVM中，该方法的抗噪性能最好，分类性能最强。

关键词: 模糊支持向量机, 隶属度函数, 类向心度

Abstract:

The traditional support vector machine (SVM) often falls into overfitting when outliers are contained in the training data. The fuzzy support vector machine can effectively deal with this problem. According to the deficiency of the membership function designed based on the distance between a sample and its cluster center, a novel fuzzy support vector machine based on the class centripetal degree (CCDFSVM) is proposed. It combines the distance between a sample and its cluster center with the relationship between samples expressed as the class centripetal degree. This function can effectively separate the valid samples from the noises or outliers. Besides, the size of the class centripetal degree can reflect the samples mixed degree. Experimental results show that the fuzzy support vector machine based on the class centripetal degree is more robust than the traditional support vector machine, and it outperforms the other two FSVM counterparts with different membership functions in terms of antinoise and classification performance.

Key words: fuzzy support vector machine;membership function;class centripetal degree

许翠云，业宁. 基于类向心度的模糊支持向量机[J]. J4, 2014, 36(08): 1623-1628.

XU Cuiyun,YE Ning. A novel fuzzy support vector
machine based on the class centripetal degree [J]. J4, 2014, 36(08): 1623-1628.

参考文献［7］

［1］	Vapnik V.The nature of statistical learning theory［M］.NY:Springer,1995.
［2］	Lin C F,Wang S D.Fuzzy support vector machine［J］.IEEE Transactions on Neural Networks(S10459227),2002,13(2):464471.
［3］	Zhang Xiang,Xiao Xiaoling,Xu Guangyou.Determination and analysis of fuzzy membership for SVM［J］.Journal of Image and Graphics,2006,11(8):11881192.(in Chinese)
［4］	Liu Chang,Sun Deshan.Determination method of membership of fuzzy SVM［J］.Computer Engineering and Applications,2008,44(11):4143.(in Chinese)
［5］	Cheng Jia,Sun Deshan.Approach of removing noises and outliers for SVM based on fuzzy membership［J］.Computer Engineering and Design,2008,29(14):37303731.(in Chinese)
［6］	Zhou Guangqian,Xu Weihong,Yang Zhiyong.A new fuzzy support vectors machine algorithm［J］.Software Space,2010,26(10):217218.(in Chinese)
［7］	Zhang Hui.Improved fuzzy support vector machine and its application［J］.Journal of Anhui Agricultural Sciences,2011,39(23):1440614409.(in Chinese)
［8］	Tao Qing,Wang Jue.A new fuzzy support vector machine based on the weighted margin［J］.Neural Processing Letters,2004,20:139150.
［9］	Xiu Fengjiang,Zhang Yi,Jian Chenglv.Fuzzy SVM with a new fuzzy membership function［J］.Neural Comput & Applic,2006(15):268276.
［10］	He Qiang,Wu Congxin.Membership evaluation and feature selection for fuzzy support vector machine based on fuzzy rough sets［J］.Soft Comput,2011(15):11051114.
［11］	Sabzeka M,Yazdi H S,Naghibzadeh M.Relaxed constraints support vector machines for noisy data［J］.Neural Comput & Applic,2011(20):671685.
	附中文参考文献：
［3］	张翔,肖小玲,徐光佑.模糊支持向量机中隶属度的确定与分析［J］.中国图像图形学报,2006,11(8):11881192.
［4］	刘畅,孙德山.模糊支持向量机隶属度的确定方法［J］.计算机工程与应用,2008,44(11):4143.
［5］	程佳,孙德山.基于模糊隶属度的支持向量机去噪方法［J］.计算机工程与设计,2008,29(14):37303731.
［6］	周广千,徐蔚鸿,杨志勇.一种新的模糊支持向量机算法［J］.软件时空,2010,26(10):217218.
［7］	章慧.改进模糊支持向量机方法及其应用［J］.安徽农业科学,2011，39(23):1440614409.

[1]	方宁1,2，谭飞2. 基于改进F-SVM算法的雷达距离像目标识别[J]. J4, 2013, 35(6): 82-87.
[2]	赵剑辉1，凌卫新1，陈卓铭2，何敏聪1，欧阳静明2. 基于模糊多类支持向量机的声母识别方法[J]. J4, 2011, 33(5): 160-164.

基于类向心度的模糊支持向量机

A novel fuzzy support vector
machine based on the class centripetal degree

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献［7］

相关文章 2

编辑推荐

Metrics

本文评价

基于类向心度的模糊支持向量机

A novel fuzzy support vector machine based on the class centripetal degree

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献 ［7］

相关文章 2

编辑推荐

Metrics

本文评价

A novel fuzzy support vector
machine based on the class centripetal degree

参考文献［7］