首页 | 本学科首页   官方微博 | 高级检索  
     

基于MPI的并行PSO混合K均值聚类算法
引用本文:吕奕清,林锦贤. 基于MPI的并行PSO混合K均值聚类算法[J]. 计算机应用, 2011, 31(2): 428-431. DOI: 10.3724/SP.J.1087.2011.00428
作者姓名:吕奕清  林锦贤
作者单位:福州大学数学与计算机科学学院
基金项目:福建省高校科研专项重点项目资助项目
摘    要:传统的串行聚类算法在对海量数据进行聚类时性能往往不尽如人意,为了适应海量数据聚类分析的性能要求,针对传统聚类算法的不足,提出一种基于消息传递接口(MPI)集群的并行PSO混合K均值聚类算法。首先将改进的粒子群与K均值结合,提高该算法的全局搜索能力,然后利用该算法提出一种新的并行聚类策略,并将该算法与K均值聚类算法、粒子群优化(PSO)聚类算法进行比较。实验结果表明,该算法不仅具有较好的全局收敛性,而且具有较高的加速比。

关 键 词:消息传递接口集群  粒子群优化算法  K均值算法  并行聚类  
收稿时间:2010-07-14
修稿时间:2010-09-04

Parallel PSO combined with K-means clustering algorithm based on MPI
L Yi-qing,LIN Jin-xian. Parallel PSO combined with K-means clustering algorithm based on MPI[J]. Journal of Computer Applications, 2011, 31(2): 428-431. DOI: 10.3724/SP.J.1087.2011.00428
Authors:L Yi-qing  LIN Jin-xian
Affiliation:L(U) Yi-qing,LIN Jin-xian
Abstract:The performance of traditional serial clustering algorithm cannot meet the needs of data clustering of the huge amounts of data. To enhance the performance of clustering algorithm, a new clustering algorithm combining parallel Particle Swarm Optimization (PSO) with K-means based on MPI was proposed in this paper. Firstly, the improved PSO was combined with K-means to enhance the capacity of global search, and then a new parallel clustering algorithm was proposed, which was compared with K-means and PSO clustering algorithms. The experimental results show that the new algorithm has better global convergence, and also has higher speed-up ratio.
Keywords:Message Passing Interface (MPI) cluster   Particle Swarm Optimization (PSO) algorithm   K-means algorithm   parallel clustering
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《计算机应用》浏览原始摘要信息
点击此处可从《计算机应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号