基于RBF核的SVM及RVM模式分析性能比较  

Comparison on pattern analysis performance of SVM and RVM based on RBF kernel

作　　者：李刚[1,2] 邢书宝[1] 薛惠锋[1] 

机构地区：[1]西北工业大学自动化学院,西安710072 [2]西安工业大学经管学院,西安710032

出　　处：《计算机应用研究》2009年第5期1782-1784,共3页Application Research of Computers

基　　金：陕西省教育厅专项科研计划资助项目(08JK312)

摘　　要：基于RBF核,利用Synthc、BC等标准数据集,采用五重交叉验证,比较SVM(支持向量机)及RVM(关联向量机)模式分析性能。实验结果表明,与SVM相比,RVM时间复杂度、测试错误率较低,模式分析性能较优。Making use of standard dataset such as synth and BC, compared the pattren analysis performance of SVM and RVM using 5-fold verification based on RBF kernel. Test result indicates that the mistake rate and time complication degree is lower than that of SVM. Research shows under the condition of this paper RVM＇ s pattern analysis performance is more excellent.

关 键 词：关联向量机 支持向量机 分类 径向基函数核 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]