用核K-means聚类减样法优化半定规划支持向量机  

Using Kernel K-Means Clustering Reducing Method for the Optimization of Semi-Definite Programming SVM

作　　者：何慧[1] 胡小红 覃华[3] 张敏[3] 

机构地区：[1]江西师范大学商学院电子商务系,江西南昌330022 [2]抚州市党校,江西抚州344000 [3]广西大学计算机与电子信息学院,广西南宁530004

出　　处：《江西师范大学学报（自然科学版）》2013年第6期574-578,共5页Journal of Jiangxi Normal University(Natural Science Edition)

基　　金：国家自然科学基金(61063032);教育部人文社会科学研究规划基金(1YJAZH080)资助项目

摘　　要：提出了使用核空间K-means聚类算法从训练集中抽取特征边界支持向量集,在边界集上构造支持向量机的半定规划问题,由于边界集的规模比原始训练集要小,降低了半定规划支持向量机的规模,达到优化向量机的目的.在UCI数据集上的实验结果表明:所提优化方法在求解多核半定规划向量机时,比原始方法获得几倍以上的速度提升,分类精度基本不变.Kernel K-means clustering method is proposed for abstracting the border support vector data set from training data set. The semi-definite programming SVM is solved on border set. The SVM scale is reduced as the bor- der set is less than the original training data set, and the optimization of semi-definite programming is implemented. The experimental results on UCI data set show that the new SVM training time is several times less than the original one and the classification accuracy of new SVM is equals to original one.

关 键 词：支持向量机 半定规划 核K—means聚类 减样 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]