Fuzzy SVM with a new fuzzy membership function

被引：264

作者：

Jiang, Xiufeng ^{[1
]}

Yi, Zhang ^{[1
]}

Lv, Jian Cheng ^{[1
]}

机构：

[1] Univ Elect Sci & Technol China, Computat Intelligence Lab, Sch Comp Sci & Engn, Chengdu 610054, Peoples R China

来源：

NEURAL COMPUTING & APPLICATIONS | 2006年 / 15卷 / 3-4期

关键词：

support vector machine; fuzzy support vector machine; fuzzy membership function; quadratic programming;

D O I：

10.1007/s00521-006-0028-z

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];

摘要：

It is known that with a proper fuzzy membership function, a fuzzy support vector machine can effectively reduce the effects of outliers when solving the classification problem. In this paper, a new fuzzy membership function is proposed to the nonlinear fuzzy support vector machine. The fuzzy membership is calculated in the feature space and is represented by kernels. This method gives good performance on reducing the effects of outliers and significantly improves the classification accuracy and generalization.

引用

页码：268 / 276

页数：9

共 12 条

[1]

[Anonymous], 1997, THESIS TU BERLIN GER

[2]

Burges C., 1996, P 13 INT C MACH LEAR

[3]

CORTES C, 1995, MACH LEARN, V20, P273, DOI 10.1023/A:1022627411411

[4]

Courant, 1953, METHODS MATH PHYS

[5]

Graf A. B. A., 2003, IEEE T NEURAL NETW, V14

[6]

GUYON I, 1996, DISCOVERING INFORM P

[7]

HERBRICH R, 2001, P 9 ICANN, V2, P649

[8]

Fuzzy support vector machines [J].

Lin, CF ;

Wang, SD .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002, 13 (02) :464-471

[9]

Successive overrelaxation for support vector machines [J].

Mangasarian, OL ;

Musicant, DR .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (05) :1032-1037

[10]

Robust support vector machine with bullet hole image classification [J].

Song, Q ;

Hu, WJ ;

Xie, WF .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS, 2002, 32 (04) :440-448

← 1 2 →