计算机技术与发展Issue(9)：53-56,4.DOI:10.3969/j.issn.1673-629X.2015.09.011
一种密度和划分结合的聚类算法
A Clustering Algorithm of Combination of Density and Division
摘要
Abstract
Both the density-based clustering algorithm DBSCAN and the division-based clustering algorithm k-means have their advan-tages and disadvantages. In order to reduce the sensitivity of clustering algorithm to the parameters and the input order of the data points, finding clusters of arbitrary shape and improving the quality of clustering mining,on the basis of DBSCAN and k-means clustering algo-rithm,propose a clustering algorithm combined density and division,named DDCA. This algorithm firstly calculates the density of data points,then combines the center point which has a density greater than a given threshold value and others point which in the density range of the center point to build basic clusters. Then merge two basic clusters according to the distance between their center points. Finally,di-vide point which is not belong to any cluster into its nearest cluster. Theoretical analysis and experimental results on KDD CUP 99 dataset show that this algorithm can find clusters of arbitrary shape,and is not sensitive to parameters and the input order of data points. It can get higher clustering accuracy with a little additional time cost. Its overall performance is better than k -means clustering algorithm.关键词
数据挖掘/k -means/DBSCAN/聚类/密度/划分Key words
data mining/k -means/DBSCAN/clustering/density/division分类
信息技术与安全科学引用本文复制引用
王玉雷,李玲娟..一种密度和划分结合的聚类算法[J].计算机技术与发展,2015,(9):53-56,4.基金项目
国家“973”重点基础研究发展计划项目(2011CB302903) （2011CB302903）
