期刊文献+

FCCM算法中基于划分熵的参数优选方法 被引量:2

A method of parameter optimization based on partition entropy in FCCM algorithm
下载PDF
导出
摘要 针对在FCCM及其改进算法中,模糊控制参数Tu往往采用经验值,或者通过多次实验选取最佳的Tu值。在考察了模糊控制参数Tu对于聚类结果的影响和在使用划分熵的变化来衡量聚类结果的明晰程度的基础上,引入隶属度矩阵的平均方差来对模糊控制参数Tu的取值进行限制,通过约束聚类的模糊程度,提出一种基于划分熵的参数优选方法。数据实验表明,使用该方法自动确定的参数Tu可减少直接使用经验值或多次实验选取最佳值时的随机性和偶然性,帮助FCCM算法获得更加稳定的聚类结果。 In FCCM and its improved algorithms,Tuis assigned based on experiences or the trial and error approach. the effect of fuzzy control parameter Tuinvestigates on the clustering results of FCCM algorithm,constraining the degree of fuzzy clustering,a parameter optimization method based on partition entropy. Data experiments show that the parameter automatically determined by the proposed method can improve the clustering quality of FCCM algorithm effectively.
出处 《河南理工大学学报(自然科学版)》 CAS 北大核心 2016年第2期248-253,273,共7页 Journal of Henan Polytechnic University(Natural Science)
基金 国家自然科学基金资助项目(61202286) 河南省高等学校青年骨干教师计划项目(20156GJS-068)
关键词 模糊联合聚类 模糊控制参数 划分熵 聚类算法 fuzzy co-clustering fuzzy control parameter partition entropy clustering alogrithm
  • 相关文献

参考文献11

  • 1刘永利,付丽丽.一种改进的社区探测方法[J].河南理工大学学报(自然科学版),2015,34(1):91-95. 被引量:1
  • 2黄少滨,杨欣欣,申林山,李艳梅.高阶异构数据模糊联合聚类算法[J].通信学报,2014,35(6):15-24. 被引量:8
  • 3OH C, HONDA K, ICHIHASHI H, et al. Fuzzy cluste- ring for categorical multivariate data [ C ]//Ifsa World Congress & Nafips International Conference. IEEE, 2001:2154 - 2159.
  • 4OH C H, HONDA K. Dual Exclusive Partition in Fuzzy CoDoK and SCAD-based Fuzzy Co-clustering [ J]. Pro- cedia Computer Science ,2013:800-809.
  • 5MATSUMOTO Y, HONDA K, NOTSU A, et al. FCM- type co-clustering of categorical multivariate data with exclusive partition[ C [// Soft Computing and Intelli- gent Systems (SCIS) and 13th International Symposi- um on Advanced Intelligent Systems (ISIS), 2012 Joint 6th International Conference on. IEEE, 2012: 1796 -1800.
  • 6TJHI W C,CHEN L. Dual Fuzzy-Possibilistic Co-cluste- ring for Document Categorization [ J ]. Data Mining Workshops icdm Workshops seventh IEEE Internation- al Conference on,2007:259-264.
  • 7MURANISHI M, HONDA K, NOTSU A, et al. A cluster validity index for FCM-type co-clustering[ C ]/Hydera- bad, India: Institute of Electrical and Electronics En- gineers Inc. , 2013.
  • 8TJHI W,CHEN L. A heuristic-based fuzzy co-clustering algorithm for categorization of high-dimensional data [Jl. Fuzzy Sets & Systems,2008,159(4) :371-389.
  • 9WU K L. Analysis of parameter selections for fuzzy c- means [ J ]. Pattern Recognition, 2012,45 ( 1 ) : 407- 415.
  • 10YAN Y, CHEN L,TJHI W C. Fuzzy semi-supervised co-clustering for text documents [ J ]. Fuzzy Sets & Sys- tems ,2013,215 ( 3 ) :74-89.

二级参考文献48

  • 1宫改云,高新波,伍忠东.FCM聚类算法中模糊加权指数m的优选方法[J].模糊系统与数学,2005,19(1):143-148. 被引量:81
  • 2Duda R O,Hart P E. Pattern classification and scene analysis [ DB]. John Wiley & Sons,New York,1973.
  • 3Dunn J C. A fuzzy relative of the ISODATA process and its use in detecting compact well separated cluster [ J ]. J Cybemet ,1974 ,3 ( 1 ) :32 - 57.
  • 4Bezdek J C. Fuzzy mathematics in pattern classification [ D ]. ComeU Univ. , Ithaca, NY, 1973.
  • 5Bezdek J C. Pattern recognition with fuzzy objective function algorithms [ M ]. New York: Plenum, 1981.
  • 6Bezdek J C. A physical interpretation of fuzzy ISODATA [ J ]. IEEE Trans. Syst. Man Cybem. , 1976,6:387 - 390.
  • 7Cheung Y S, Chan K P. Modified fuzzy ISODATA for the classification of handwritten Chinese characters [ A ]. Proc. 1986, Int. Conf. Chinese Compot. [ C ], Singapore, 1986.:361 - 364.
  • 8Bezdek J C, Hathaway R J, et al. Convergence and theory for fuzzy c - means clustering:counterexamples and repairs [ J ]. IEEE Trans. Syst. Man Cybern. , 1987,17 (5) :873 - 877.
  • 9Pal N R, Bezdek J C. On cluster validity for the fuzzy c-means model [ J ]. IEEE Tran. Fuzzy Systems, 1995,3 (3) :370 - 379.
  • 10章小平.基于塔形模糊聚类的纹理分割方法[M].西安:西安电子科技大学,2003:22-33.

共引文献12

同被引文献20

引证文献2

二级引证文献16

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部