Robust proximal support vector machine
-
摘要: 标准近似支持向量机受类别差异影响和噪声、野值数据干扰较重,使得分类能力不高.提出一种改进的近似支持向量机算法——加权近似支持向量机,通过为不同类别设定不同的惩罚参数和为每个样本引入模糊隶属值,有效补偿类别差异带来的倾向性并去除噪声和野值数据的影响.模糊隶属函数的选取采用样本与类中心的距离和样本紧密度的加权平均值计算,以有效去除噪声和野值数据的干扰.经过分析,改进后的算法可近似归结为一种岭回归模型.实验表明,与标准近似支持向量机相比,该算法有更好的分类能力.Abstract: Since proximal support vector machine(PSVM) is susceptible to uneven class sizes and is sensitive to outliers and noises in the training set, a robust PSVM was proposed. By imposing fuzzy memberships to each data point and introducing different error penalties for different classes, the robustness of PSVM was greatly enhanced. Both the affinity among samples and the relation between a sample and its class center were considered when calculating fuzzy memberships. Moreover, the similarity between the algorithm and ridge regression model was well demonstrated. Experiment results show that the robust PSVM has demonstrated enhanced classification ability.
-
Key words:
- classification /
- support vector machine /
- uneven class sizes /
- fuzzy memberships
-
[1] 邓乃扬,田英杰. 数据挖掘中的新方法——支持向量机[M]. 北京:科学出版社,2004 Deng Naiyang,Tian Yingjie. A new method of datamining:SVM[M]. Beijing:Science Press,2004(in Chinese) [4] Fung G, Mangasarian O L. Proximal support vector machine classifiers Proceedings of the Seventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM,2001:77-86 [2] Chew H G, Bogner R E, Lim C C. Dual ν-support vector machine with error rate and training size biasing ICASSP IEEE Int Conf Acoust Speech Signal Process Proc. Piscataway,NJ:IEEE,2001,2:1269-1272 [3] Lin Chunfu, Wang Shengde. Fuzzy support vector machines[J]. IEEE Transactions on Neural Networks, 2002, 13(2):464-471 [5] 范昕炜,杜树新,吴铁军. 可补偿类别差异的加权支持向量机算法[J]. 中国图象图形学报,2003, 8(9):1037-1042 Fan Xinwei, Du Shuxin, Wu Tiejun. Weighted support vector machine based classification algorithm for uneven class size problems[J]. Journal of Image and Graphics,2003,8(9):1037-1042(in Chinese) [6] 张翔, 肖小玲, 徐光祐. 基于样本之间紧密度的模糊支持向量机算法[J].软件学报,2006,17(5):951-958 Zhang Xiang, Xiao Xiaoling, Xu Guangyou. Fuzzy support vector machine based on affinity among samples[J]. Journal of Software, 2006,17(5):951-958(in Chinese) -
点击查看大图
计量
- 文章访问数: 2986
- HTML全文浏览量: 233
- PDF下载量: 1757
- 被引次数: 0
下载:
