J4

• • 上一篇    下一篇

基于粒子群优化算法的模糊C-均值聚类

张利彪, 周春光, 马铭, 刘小华, 孙彩堂   

  1. (吉林大学 计算机科学与技术学院, 长春 130012)
  • 收稿日期:2005-04-29 修回日期:1900-01-01 出版日期:2006-03-26 发布日期:2006-03-26
  • 通讯作者: 周春光

Fuzzy C-Mean Clustering Based on Particle Swarm Optimization

ZHANG Li-biao, ZHOU Chun-guang, MA Ming, LIU Xiao-hua, SUN Cai-tang   

  1. (College of Computer Science and Technology, Jilin University, Changchun 130012, China)
  • Received:2005-04-29 Revised:1900-01-01 Online:2006-03-26 Published:2006-03-26
  • Contact: ZHOU Chun-guang

摘要: 利用粒子群优化(PSO)算法全局寻优、 快速收敛的特点, 结合模糊C均值(FCM)算法提出一种新的模糊聚类算法. 新算法用PSO算法代替了FCM算法的基于梯度下降的迭代过程, 使算法具有很强的全局搜索能力, 很大程度上避免了FCM算法易陷入局部极小的缺陷; 同时也降低了FCM算法对初始值的敏感度. 实验结果表明, 与FCM相比本文算法聚类更为准确, 效率更高.

关键词: 粒子群优化算法, 模糊聚类, 模糊C均值算法

Abstract: A novel fuzzy clustering algorithm which uses the merits of the global optimizing and higher convergent speed of Particle Swarm Opt imization(PSO) algorithm and combines with Fuzzy C-means(FCM) is proposed. The iteration process is replaced by the PSO based on the gradient descent of FCM, which makes the algorithm have a strong global searching capacity and avoids the local minimum problems of FCM. At the same time, FCM is no longer a large degree dependent on the initialization values. Numerical experiments show that the proposed algorithm is more accurate and efficient than FCM.

Key words: particle swarm optimization algorithm, fuzzy clustering, fuzzy C-means algorithm

中图分类号: 

  • TP18