基于混沌振荡粒子群优化的FCM文本聚类方法  

The Text Clustering Method of FCM Clustering Based on Chaotic Oscillation Particle Swarm Optimization

作　　者：符保龙[1] 

机构地区：[1]柳州职业技术学院电子信息工程系,广西柳州545006

出　　处：《河池学院学报》2015年第2期74-78,共5页Journal of Hechi University

基　　金：广西教育厅科研基金资助项目(LX2014533)

摘　　要：针对模糊C均值聚类算法易于陷入局部极值的问题,设计了一种基于混沌振荡粒子群优化的模糊C均值聚类方法。该方法在标准PSO算法中设计了一个振荡环节并引入混沌理论以增加算法的多样性和收敛性,接着把优化后的PSO算法和模糊C均值聚类算法相结合。文本聚类的仿真实验表明,相对于PSO-FCM算法和FCM算法,CCPSO-FCM算法具有良好的全局搜索能力和收敛速度,聚类效果良好。As the Fuzzy C-Means clustering algorithm is easy to fall into local extremum, the author propo-ses a Fuzzy C-Means clustering method based on chaotic oscillation particle swarm optimization.Combining the PSO optimized algorithm and Fuzzy C-Means clustering algorithm, an oscillating part of chaos theory was designed and introduced in the standard particle swarm optimization algorithm so as to increase the diversity and convergence algorithm.The simulation experiments of text clustering results show that CCPSO-FCM algorithm has better global search ability and convergence speed, compared with PSO-FCM algorithm and FCM algorithm, and the clustering effect is better as well.

关 键 词：混沌优化 振荡优化 粒子群优化算法 模糊C均值聚类算法 文本挖掘 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]