一种基于PIM与核方法的模糊聚类新算法

中国管理科学 ›› 2006, Vol. ›› Issue (3): 76-79.

一种基于PIM与核方法的模糊聚类新算法

关忠诚, 熊慧琴

中国科学院科技政策与管理科学研究所, 北京, 100080

收稿日期:2005-10-20 修回日期:2006-05-20 出版日期:2006-06-28 发布日期:2012-03-07

A New Fuzzy Clustering Algorithm Based on PIM and the Kernel Method

GUAN Zhong-cheng, XIONG Hui-qin

Institute of Policy & Management, Chinese Academy of Sciences, Beijing 100080, China

Received:2005-10-20 Revised:2006-05-20 Online:2006-06-28 Published:2012-03-07

摘要/Abstract

摘要： 本文针对模糊C均值聚类在大数据量时收敛较慢以及不能对多种数据结构有效聚类的缺点,结合PIM算法与核方法提出了一种新的高效聚类算法———KPIM算法,并从理论上证明了该算法的收敛性.最后利用标准实验数据IRIS数据集测试,结果表明KPIM算法在保证收敛速度的同时,聚类效果更有效.

关键词: 模糊, 聚类, PIM算法, 核方法, KPIM算法

Abstract: The traditional "fuzzy" clustering(FCM) converges slowly when confronted with a large number of data points,meanwhile it can't deal with non-hyper spherical data structure,which compel us to present a new fuzzy clustering algorithm-the KPIM algorithm based on partition index maximization(PIM) algorithm and the kernel method.As well the paper proves convergence theorem of the new algorithm.The results of experiments on the real data show that the KPIM algorithm can effectively cluster on data with diversiform structures while guaranteeing the computation time in contrast to other previous algorithms.

Key words: fuzzy, clustering, PIM, kernel method, KPIM algorithm

中图分类号:

C931

关忠诚, 熊慧琴. 一种基于PIM与核方法的模糊聚类新算法[J]. 中国管理科学, 2006, (3): 76-79.

GUAN Zhong-cheng, XIONG Hui-qin. A New Fuzzy Clustering Algorithm Based on PIM and the Kernel Method[J]. Chinese Journal of Management Science, 2006, (3): 76-79.

参考文献

[1] Giles DEA & Draeseke R.Econometric modeling using pattern recognition via the fuzzy C-means algorithm[M].Computer-aided econometrics,2001.
[2] Bezdek,JC.Pattern Recognition with Fuzzy Objective Function Algorithms[M].Plenum Press,1981,New York.
[3] Zio,E,Baraldi,P.A fuzzy clustering approach for transients classification[J].Applied Computational Intelligence,2004.
[4] Dogan Ozdemir & Lale Akarun.Fuzzy Algorithms for Combined Quantization and Dithering[J].IEEE Transactions on Image Processing,2001,(10):923-931.
[5] Jiuh-Biing Sheu.A fuzzy clustering approach to real -time demand-responsive bus dispatching control[J].Fuzzy Sets and Systems,2005,150:437-455.
[6] Dogan Ozdemir & Lale Akarun.A fuzzy algorithm for color quantization of images[J].Pattern Recognition,2002,35:1785-1791.
[7] Girolami M.Mercer Kernel Based Clustering in Feature Space[J].IEEE Trans on Neural Networks,2002,13(3):780-784.
[8] Bezdek JC.A convergence theorem for the fuzzy ISODATA clustering algorithms[J].IEEE Trans.Pattern Anal.And Machine Intell.,1980,(2):1-8.
[9] Bezdek JC.Convergence Theory for Fuzzy C Means:Counter Examples and Repairs[J].IEEE Trans on SMC,1987,17(4):873-877.
[10] Selim SZ & Ismail MA.On the local optimality of the fuzzy ISODATA clustering algorithm[J].IEEE Trans.Pattern Anal.Mach.Intell.1986,8:284-288.
[11] Sabin J.Convergence and consistence of fuzzy c means/ISODATA algorithms[J].IEEE Trans on PAMI,1987,9(5):661-668.
[12] Jian Yu & Miin-Shen Yang.Optimality Test for Generalized FCM and Its Application to Parameter Selection[J].IEEE Trans on FUZZY SYSTEMS,2005,13(1):164-176.
[13] Ismail MA and Selim SZ.Fuzzy c-means:Optimality of the solutions and effective termination of the algorithm[J].Pattern Recognition,1986,19(6):481-485.
[14] Bezde JC & Keller JM etal.Will the Real IRIS Data Please Stand Up?[J].IEEE Trans on Fuzzy System,1999,7(3):368-369.
[15] 高新波,谢维信.模糊聚类理论发展及其应用的研究进展[J].科学通报,1999,44(21):2241-2251.
[16] 伍忠东,高新波,谢维信.基于核方法的模糊聚类算法[J].西安电子科技大学学报,31(4):533-537.