matlab svm核函数选择,SVM分类核函数及参数选择比较.pdf

Compu~r Engineering口 4 胁日ff0 计算机工程与应用

SVM分类核函数及参数选择比较

奉国和 FENG Guohe

华南师范大学 经济管理学院 信息管理系，广州 5 10006 School of Economy & Manangement，South Chma Normal University，Guangzhou 510006，China

E—mail：ghfeng@163．corn

FENG Guohe．Parameter optimizing for Support Vector M achines classifcation．Computer Engineering and Appfieations， 2011．47(3)：123．124．

Abstract：Support Vector Machine(SVM )has good performance for classification，but the perform ance is restricted by the kernel function and its parameters．This paper discusses the problem，and uses cross validation，grid searching for optimizing

the kernel function parameters． Key words：Support Vector Machines(SVM)；kemel function；classification

摘 要：支持向量机(SVM)被证实在分类领域性能良好，但其分类性