作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2007, Vol. 33 ›› Issue (22): 198-199. doi: 10.3969/j.issn.1000-3428.2007.22.068

• 人工智能及识别技术 • 上一篇    下一篇

一种基于微粒群的模糊聚类算法

陈治亚1,方小斌1,2,雷定猷1   

  1. (1. 中南大学交通运输工程学院,长沙 410075;2. 湖南科技职业学院,长沙 410004)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-11-20 发布日期:2007-11-20

Fuzzy Clustering Algorithm Based on Particle Swarm

CHEN Zhi-ya1, FANG Xiao-bin1,2, LEI Ding-you1   

  1. (1. School of Traffic and Transportation Engineering, Central South University, Changsha 410075; 2. Hunan Vocational College of Science and Technology, Changsha 410004)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-11-20 Published:2007-11-20

摘要: 模糊聚类的FCM算法由于得不到各聚类的解析解,使其在某些应用中出现问题。为此,该文提出了一种基于微粒群理论的模糊聚类方法,利用微粒群自动调整各模糊聚类的中心点及其隶属函数参数,使模糊聚类符合数据分布特征,同时得到各聚类的隶属函数解析解。通过典型模糊分类问题,说明了该算法的有效性。

关键词: 模糊聚类, 微粒群算法, FCM算法, 模糊分类

Abstract: Since analytic solution of the fuzzy cluster can not be gained by FCM algorithm, the algorithm is not convenient in some applications. This paper proposes a new fuzzy cluster strategy based on particle swarm algorithm(PSO). By using particle swarm algorithm to adjust the center and membership function parameter of the fuzzy cluster automatically, result of fuzzy cluster can be adapted to the feature of data distribution and the membership function for each fuzzy cluster can be obtained. The effectiveness of the method is demonstrated by typical fuzzy classification problem.

Key words: fuzzy cluster, particle swarm algorithm, FCM algorithm, fuzzy classification

中图分类号: