基于MapReduce的K-means聚类集成  

K-means Clustering Ensemble Based on MapReduce

作　　者：冀素琴[1] 石洪波[1] 

机构地区：[1]山西财经大学信息管理学院,太原030031

出　　处：《计算机工程》2013年第9期84-87,共4页Computer Engineering

基　　金：国家自然科学基金资助项目(60873100);山西省自然科学基金资助项目(2010011022-1)

摘　　要：针对传统聚类算法难以高效进行海量数据聚类分析的问题,提出一种基于MapReduce框架的K-means聚类集成算法。利用K-means算法生成不同聚簇数目的基聚类结果,改进共协关系矩阵,依据数据点对出现次数进行集成,自动得出最终聚类结果。实验结果表明,该算法能够有效地改善聚类质量,具有良好的扩展性,适用于海量数据的聚类分析。Aiming at the problem of the clustering analysis on massive data for traditional clustering algorithm, this paper proposes a K-means clustering ensemble algorithm based on MapReduce. It generates component clustering results with different number of cluster by the K-means algorithm, improves co-association matrix, and gets a final result automatically via the number of times sample pair co-occurred. Experimental results show that this algorithm can effectively improve the quality of clustering, and has good scalability, fits to clustering analysis on massive data.

关 键 词：海量数据 聚类 MAPREDUCE框架 K—means算法 共协关系矩阵 聚类集成 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]