一种改进的支持向量聚类算法  

An improved algorithm for support vector clustering

作　　者：程丽[1] 周亚建[1] 

机构地区：[1]北京邮电大学信息安全中心,北京中国100876

出　　处：《北京电子科技学院学报》2011年第4期1-9,共9页Journal of Beijing Electronic Science And Technology Institute

基　　金：国家高技术研究发展计划(863计划)(No.2009AA01Z430);国家自然科学基金(No.60972077;60973146)

摘　　要：为了提高算法聚类精度,降低算法聚类耗时,根据支持向量聚类算法的统计性原理本文提出了一种改进的支持向量聚类算法。该算法通过预处理数据,提高样本质量;成功解决内部支持向量点扰乱提取簇轮廓的问题;利用支持向量点寻找局部最优点,采用SEP进行成对抽样确定簇标签。理论分析和仿真结果表明,改进算法有效的提高了聚类精度高,降低了算法的复杂度。According to support vector cluster algorithm＇s statistical principle, this paper proposes an improved support vector cluster algorithm which can increase the precision of the clustering, and reduce the time-consuming. The algorithm, pre-processing noise data, improves the sample data quality, solves the internal support vector data harassment extraction profile bunch of the cluster, seeks for the partial optimum point using the support vector points and determines cluster labels by using stable equilibrium points to carry on the geminate sampling determination cluster labels. The theoretical analysis and the simulation result indicated that the improved algorithm enhances the precision of the clustering, and reduces the time complexity of the algorithm. The algorithm has achieved good clustering results.

关 键 词：支持向量聚类 预处理噪声 抽样 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]