自适应局部半径的DBSCAN聚类算法  

Self-adaptive Local eps DBSCAN

作　　者：秦佳睿 徐蔚鸿[1] 马红华 曾水玲 QIN Jia-rui;XU Wei-hong;MA Hong-hua;ZENG Shui-ling(School of Computer ＆ Communication Engineering,Changsha University of Science and Technology,Changsha 410114,China;Zixing Municipal Bureau of Science and Technology of Hunan Province,Chenzhou 423400,China;JiShou University College of Information Science ＆ Enginnering,Jishou 416000,China)

机构地区：[1]长沙理工大学计算机与通信工程学院,长沙410114 [2]湖南省资兴市科学技术局,湖南郴州423400 [3]吉首大学信息科学与工程学院,湖南吉首416000

出　　处：《小型微型计算机系统》2018年第10期2186-2190,共5页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(61363033)资助;湖南省科技服务平台基金项目(2012TP1001)资助

摘　　要：经典的基于密度的聚类方法 DBSCAN算法需要指定邻域半径和最小数据点阈值两个基本参数.这两个参数的确定对聚类结果的影响非常大.目前缺少有效的参数选择确定方法,同时DBSCAN算法在聚类过程中,使用统一的邻域半径参数,使得密度不均匀集上的聚类质量不高.本文提出一种自适应选择局部半径的密度聚类算法(SALE-DBSCAN),通过确定密度峰值点,自适应选择聚类的局部邻域半径,简化了参数选择的过程;通过使用自适应选择的局部邻域半径扩张密度峰值点的邻域进行聚类,提高了聚类结果质量.实验结果表明,本SALE-DBSCAN算法相较其他密度聚类算法的聚类结果更加准确.DBSCAN requires users set two basic parameters artificially, eps and minPts. They have an important influence for clustering results. At present,there is a lack of effective methods about selecting parameters. Meanwhile ,DBSCAN uses global parameters during clustering, which leads to clustering quality is poor in data sets with different densities. This paper proposed a Self-Adaptive Local eps DBSCAN （SALE-DBSCAN） ,simplifying process of parameters selection by confirming points with density peak and self-adaptive selecting local neighborhood eps of clustering; Improving clustering quality by using self-adaptive local eps expands neighborhoods of points with density peak. The experiment shows our algorithm＇s clustering quality is better than other based-density clustering algorithms.

关 键 词：密度聚类 DBSCAN 密度峰值 自适应局部半径 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]