Abstract
Suppressed fuzzy c-means (s-FCM) clustering was introduced in Fan et al. (Pattern Recogn Lett 24:1607–1612, 2003) with the intention of combining the higher speed of hard c-means (HCM) clustering with the better classification properties of fuzzy c-means (FCM) algorithm. The authors modified the FCM iteration to create a competition among clusters: lower degrees of memberships were diminished according to a previously set suppression rate, while the largest fuzzy membership grew by swallowing all the suppressed parts of the small ones. Suppressing the FCM algorithm was found successful in the terms of accuracy and working time, but the authors failed to answer a series of important questions. In this paper, we clarify the view upon the optimality and the competitive behavior of s-FCM via analytical computations and numerical analysis. A quasi competitive learning rate (QLR) is introduced first, in order to quantify the effect of suppression. As the investigation of s-FCM’s optimality did not provide a precise result, an alternative, optimally suppressed FCM (Os-FCM) algorithm is proposed as a hybridization of FCM and HCM. Both the suppressed and optimally suppressed FCM algorithms underwent the same analytical and numerical evaluations, their properties were analyzed using the QLR. We found the newly introduced Os-FCM algorithm quicker than s-FCM at any nontrivial suppression level. Os-FCM should also be favored because of its guaranteed optimality.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Anderson E (1935) The IRISes of the Gaspe peninsula. Bull Am IRIS Soc 59:2–5
Arthur D, Vassilvitskii S (2007) k-means++: the advantages of careful seeding. In: Proceedings of Symposium on Discrete Algorithms, pp 1027–1035
Asuncion A, Newman DJ (2007) UCI machine learning repository. University of California, School of Information and Computer Science, Irvine. Available at: http://www.ics.uci.edu/∼mlearn/MLRepository.html
Baraldi A, Blonda P (1999) A survey of fuzzy clustering algorithms for pattern recognition. IEEE Trans Syst Man Cybern Part B 29:778–801
Barni M, Capellini V, Mecocci A (1996) Comments on a possibilistic approach to clustering. IEEE Trans Fuzzy Syst 4:393–396
Benyó B, Somogyi P, Paláncz B (2006) Classification of time series using singular values and wavelet subband analysis with ANN and SVM classifiers. J Adv Comput Intell Intell Inform 10:498–503
Bezdek JC (1981) Pattern recognition with fuzzy objective function algorithms. Plenum, New York
Bezdek JC, Keller J, Krishnapuram R, Pal NR (1999) Fuzzy models and algorithms for pattern recognition and image processing. Springer, New York
Cannon RL, Dave JV, Bezdek JC (1986) Efficient implementation of the fuzzy c-means clustering algorithms. IEEE Trans Patt Anal Machine Intell 8:248–255
Cheng TW, Goldgof DB, Hall LO (1998) Fast fuzzy clustering. Fuzzy Sets Syst 93:49–56
Eschrich S, Ke J, Hall LO, Goldgof DB (2003) Fast accurate fuzzy clustering through data reduction. IEEE Trans Fuzzy Syst 11:262–270
Fan JL, Zhen WZ, Xie WX (2003) Suppressed fuzzy c-means clustering algorithm. Patt Recogn Lett 24:1607–1612
Hathaway RJ, Bezdek JC (1995) Optimization of clustering by reformulation. IEEE Trans Fuzzy Syst 3:241–245
Hathaway RJ, Bezdek JC (2006) Extending fuzzy and probabilistic clustering to very large data sets. Comp Stat Data Anal 51:215–234
Hung WL, Yang MS, Chen DH (2006) Parameter selection for suppressed fuzzy c-means with an application to MRI segmentation. Patt Recogn Lett 27:424–438
Hung WL, Chang YC (2006) A modified fuzzy c-means algorithm for differentiation in MRI of ophtalmology. In: Modeling Decisions in Artificial Intelligence—MDAI 2006. LNCS, vol 3885. Springer, Heidelberg, pp 340–350
Kamel MS, Selim SZ (1994) New algorithms for solving the fuzzy clustring problem. Patt Recogn 27:421–428
Karayiannis NB, Bezdek JC (1997) An integrated approach to fuzzy learning vector quantization and fuzzy c-means clustering. IEEE Trans Fuzzy Syst 5:622–628
Kohonen T (1990) The self-organizing map. Proc IEEE 78:1474–1480
Kolen JF, Hutcheson T (2002) Reducing the time complexity of the fuzzy c-means algorithm. IEEE Trans Fuzzy Syst 10:263–267
Krishnapuram R, Keller JM (1993) A possibilistic approach to clustering. IEEE Trans Fuzzy Syst 1:98–110
Lázaro J, Arias J, Martín JL, Cuadrado C, Astarloa A (2005) Implementation of a modified fuzzy c-means clustering algorithm for real-time applications. Microproc Microsyst 29:375–380
Pal NR, Bezdek JC, Hathaway R (1996) Sequential competitive learning and the fuzzy c-means clustering algorithms. Neural Networks 9:787–796
Pal NR, Pal K, Bezdek JC (1997) A mixed c-means clustering model. In: 6th IEEE Int’l Conf Fuzzy Syst FUZZ-IEEE (Barcelona), pp 11–21
Pal NR, Pal K, Keller JM, Bezdek JC (2005) A possibilistic fuzzy c-means clustering algorithm. IEEE Trans Fuzzy Syst 13:517–530
Szilágyi L, Benyó Z, Szilágyi SM, Adam HS (2003) MR brain image segmentation using an enhanced fuzzy c-means algorithm. In: Proceedings of 25th Annual International Conference IEEE EMBC (Cancún), pp 724–726
Szilágyi L (2008) Novel image processing methods based on fuzzy logic. PhD Thesis, BME Budapest
Timm H, Borgelt C, Döring C, Kruse R (2004) An extension to possibilistic fuzzy cluster analysis. Fuzzy Sets Syst 147:3–16
Tsao ECK, Bezdek JC, Pal NR (1994) Fuzzy Kohonen clustering networks. Patt Recogn 27:757–764
Vapnik V (1998) Statistical learning theory. Wiley, New York
Wei LM, Xie WX (2000) Rival checked fuzzy c-means algorithm. Acta Electr Sin 28:63–66
Xie Z, Wang S, Chung FL (2008) An enhanced possibilistic c-means clustering algorithm. Soft Computing 12:593–611
Yair E, Zeger K, Gersho A (1992) Competitive learning and soft competition for vector quantization design. IEEE Trans Sign Proc 40:294–309
Zadeh LA (1965) Fuzzy sets. Inform Contr 8:338–353
Acknowledgments
This research was supported in part by the Hungarian National Office for Research and Technology, the Sapientia Institute for Research Programmes, and the Communitas and Eurotrans Foundations of Transylvania.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Szilágyi, L., Szilágyi, S.M. & Benyó, Z. Analytical and numerical evaluation of the suppressed fuzzy c-means algorithm: a study on the competition in c-means clustering models. Soft Comput 14, 495–505 (2010). https://doi.org/10.1007/s00500-009-0452-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-009-0452-y