[1]GU Wenxiang,GUO Liping,YIN Minghao.A solution for a fuzzy clustering problem by applying fuzzy c-means algorithm and gravitational search algorithm[J].CAAI Transactions on Intelligent Systems,2011,6(6):520-525.
Copy

A solution for a fuzzy clustering problem by applying fuzzy c-means algorithm and gravitational search algorithm

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 6 Number of periods: 2011 6 Page number: 520-525 Column: 学术论文—人工智能基础 Public date: 2011-12-25
Title:
A solution for a fuzzy clustering problem by applying fuzzy c-means algorithm and gravitational search algorithm
Author(s):
GU Wenxiang;  GUO Liping;  YIN Minghao
Department of Computer Science and Information Technology, Northeast Normal University, Changchun 130117, China
Keywords:
fuzzy clustering problem;  fuzzy cmeans algorithm;  gravitational search algorithm;  fuzzy gravitational search algorithm
CLC:
TP301.6
DOI:
-
Abstract:
Aiming at fixing the shortcomings of using fuzzy Cmeans algorithm solely to solve fuzzy clustering problems, first, this paper proposed an improved gravitational search algorithm by updating the velocity of individuals according to a probability, expanding the search space effectively. Secondly, a fuzzy gravitational search algorithm (FGSA) was proposed. Finally, a novel hybrid algorithm (FGSAFCM) based on a fuzzy improved gravitational search algorithm (FGSA) and fuzzy cmeans algorithm (FCM) was proposed to solve fuzzy clustering problems. Fuzzy cmeans algorithm is very sensitive to initialization and easily gets into local optima, but the new algorithm may avoid these shortcomings. This paper chooses the objective function and validity function as the evaluation criterion. The FGSAFCM was tested on ten classic datasets, and the experiment results show that the new algorithm is more accurate and robust than the sole fuzzy cmeans algorithm.
References:
［1］DUBES R C, JAIN A K. Algorithms for clustering data［M］. Englewood Cliffs, USA: Prentice Hall, 1988: 120.
［2］BEZDEK J C. Pattern recognition with fuzzy objective function algorithms［M］. New York，USA: Plenum Press, 1981： 4393.
［3］KRISHNAPURAM R, KELL J M. The possibilistic cmeans algorithm: insights and recommendation［J］. IEEE Trans FS, 1996, 4(3): 385393.
［4］RASHEDI E, NEZAMABADIPOUR H, SARYAZDI S. GSA: a gravitational search algorithm［J］. Information Sciences, 2009, 179(13): 22322248.
［5］BEZDEK J C. Fuzzy mathematics in pattern classification［D］. Ithaca: USA Cornell University, 1973: 1842.
［6］DUNN J C. A fuzzy relative of the ISODATA process and its use in detecting compact wellseparated clusters［J］. Journal of Cybernetics, 1973, 3(1): 3257.
［7］PANG W, WANG K, ZHOU C, et al. Fuzzy discrete particle swarm optimization for solving traveling salesman problem［C］//Proceedings of the Fourth International Conference on Computer and Information Technology. Wuhan，China: IEEE CS Press, 2004: 796800.
［8］PAL S K, DUTTA M R D. Fuzzy sets and decision making approaches in vowel and speaker recognition［J］. IEEE Transactions on Systems, Man, and Cybernetics，1977, 7(8): 625629.
［9］BEZDEK J C. Cluster validity with fuzzy sets［J］. Cybernetics, 1974, 3(3): 5873.
［10］RUNKLER T A, KATE C. Fuzzy clustering by particle swarm optimization［C］//International Conference on Fuzzy Systems Vancouver Canada, 2006：601608.
［11］WANG Yingje. Fuzzy clustering analysis by using genetic algorithm［J］. ICIC, 2008, 2(4): 331337.
［12］MAULIK UJJWAL, BANDYOPADHYAY SANGHAM ITA. Genetic algorithmbased clustering technique［J］. Pattern Recognition, 2000, 33(9): 14551465.
［13］谷文祥, 李向涛, 朱磊, 等. 求解流水线调度问题的万有引力搜索算法［J］. 智能系统学报, 2010, 5(5): 411418.
?GU Wenxiang, LI Xiangtao, ZHU Lei, et al. A gravitational search algorithm for flow shop scheduling［J］. CAAI Transactions on Intelligent Systems, 2010, 5(5): 411418.
［14］ASUNCION A, NEWMAN D J. UCI machine learning repository［DB/OL］. Irvine, USA: University of California,School of Information and Computer Science, 2007.
Similar References:

Memo

-

Last Update: 2012-02-29

Copyright © CAAI Transactions on Intelligent Systems