计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (18): 17-18.

• 博士论坛 • 上一篇    下一篇

不同相似度测量方式的模糊C均值聚类分析

李 中,苑津莎   

  1. 华北电力大学 电气与电子工程学院,河北 保定 071003
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-06-21 发布日期:2011-06-21

Cluster analysis of fuzzy C-mean algorithm based on different similarity estimation distances

LI Zhong,YUAN Jinsha   

  1. School of Electrical and Electronic Engineering,North China Electric Power University,Baoding,Hebei 071003,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-06-21 Published:2011-06-21

摘要: 聚类技术是机器学习、模式识别及数据挖掘等领域中的一个重要研究内容。采用不同相似度测量方式,应用标准模糊C均值聚类算法在UCI的三个知名数据集上完成聚类实验,从正确率和运行效率两个方面对比分析其性能,为聚类分析研究提供了有益的参考。

关键词: 聚类分析, 模糊C均值, 相似度

Abstract: Clustering is a key technology widely used in machine learning,pattern recognition,and data mining.Based on different similarity estimation methods,Fuzzy C-Means(FCM) clustering simulation experiments are implemented on three UCI known data sets,test results are analyzed from both sides of accuracy and running efficiency,and it can give a valuable reference for data clustering.

Key words: cluster analysis, Fuzzy C-Means(FCM), similarity