首页 | 官方网站   微博 | 高级检索  
     

一种改进的模糊聚类算法
引用本文:周红芳,宋姣姣,罗作民.一种改进的模糊聚类算法[J].计算机应用,2010,30(5):1277-1279.
作者姓名:周红芳  宋姣姣  罗作民
作者单位:1. 西安理工大学2. 3. 西安理工大学计算机科学与工程学院
基金项目:国家863计划项目(2007AA010305);;陕西省自然科学基础研究计划项目(SJ08-ZT14;SJ08-ZT15);;陕西省教育厅科学研究计划资助项目(06JK229;09JK638)
摘    要:传统模糊聚类算法如模糊C-均值(FCM)算法中,用户必须预先指定聚类类别数C,且目标函数收敛速度过慢。为此,将粒度分析原理应用在FCM算法中,提出了基于粒度原理确定聚类类别数的方法,并采用密度函数法初始化聚类中心。实验结果表明,改进后的聚类算法能够得到合理有效的聚类数目,并且与随机初始化相比,迭代次数明显减少,收敛速度明显加快。

关 键 词:模糊C-均值    粒度分析原理    耦合度    分离度    密度函数
收稿时间:2009-11-11
修稿时间:2010-01-07

Improved fuzzy clustering algorithm
ZHOU Hong-fang,SONG Jiao-jiao,LUO Zuo-min.Improved fuzzy clustering algorithm[J].journal of Computer Applications,2010,30(5):1277-1279.
Authors:ZHOU Hong-fang  SONG Jiao-jiao  LUO Zuo-min
Affiliation:School of Computer Science and Engineering/a>;Xi'an University of Technology/a>;Xi'an Shaanxi 710048/a>;China
Abstract:In traditional Fuzzy C-Means (FCM) algorithm,the user must give the number of clusters in advance and the objective function converges slowly.To solve these problems,a new algorithm for finding the best number of clusters was proposed with introducing granular analysis principle into FCM clustering algorithm,and density function algorithm was adopted to initialize the cluster centers.The experimental results show that the proposed algorithm can obtain reasonable and effective number of clusters.Compared wit...
Keywords:Fuzzy C-Means (FCM)                                                                                                                        granular analysis principle                                                                                                                        coupling degree                                                                                                                        separating degree                                                                                                                        density function
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-23

京公网安备 11010802026262号