Skip to main content
SpringerLink
Log in

Analytical and numerical evaluation of the suppressed fuzzy c-means algorithm: a study on the competition in c-means clustering models

  • Focus
  • Published:
Soft Computing Aims and scope Submit manuscript

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.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  • Anderson E (1935) The IRISes of the Gaspe peninsula. Bull Am IRIS Soc 59:2–5

    Google Scholar 

  • 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

    Article  Google Scholar 

  • Barni M, Capellini V, Mecocci A (1996) Comments on a possibilistic approach to clustering. IEEE Trans Fuzzy Syst 4:393–396

    Article  Google Scholar 

  • 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

    Google Scholar 

  • Bezdek JC (1981) Pattern recognition with fuzzy objective function algorithms. Plenum, New York

    MATH  Google Scholar 

  • Bezdek JC, Keller J, Krishnapuram R, Pal NR (1999) Fuzzy models and algorithms for pattern recognition and image processing. Springer, New York

    MATH  Google Scholar 

  • 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

    Article  MATH  Google Scholar 

  • Cheng TW, Goldgof DB, Hall LO (1998) Fast fuzzy clustering. Fuzzy Sets Syst 93:49–56

    Article  MATH  Google Scholar 

  • Eschrich S, Ke J, Hall LO, Goldgof DB (2003) Fast accurate fuzzy clustering through data reduction. IEEE Trans Fuzzy Syst 11:262–270

    Article  Google Scholar 

  • Fan JL, Zhen WZ, Xie WX (2003) Suppressed fuzzy c-means clustering algorithm. Patt Recogn Lett 24:1607–1612

    Article  MATH  Google Scholar 

  • Hathaway RJ, Bezdek JC (1995) Optimization of clustering by reformulation. IEEE Trans Fuzzy Syst 3:241–245

    Article  Google Scholar 

  • Hathaway RJ, Bezdek JC (2006) Extending fuzzy and probabilistic clustering to very large data sets. Comp Stat Data Anal 51:215–234

    Article  MATH  MathSciNet  Google Scholar 

  • 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

    Article  Google Scholar 

  • 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

    Article  Google Scholar 

  • 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

    Article  Google Scholar 

  • Kohonen T (1990) The self-organizing map. Proc IEEE 78:1474–1480

    Article  Google Scholar 

  • Kolen JF, Hutcheson T (2002) Reducing the time complexity of the fuzzy c-means algorithm. IEEE Trans Fuzzy Syst 10:263–267

    Article  Google Scholar 

  • Krishnapuram R, Keller JM (1993) A possibilistic approach to clustering. IEEE Trans Fuzzy Syst 1:98–110

    Article  Google Scholar 

  • 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

    Article  Google Scholar 

  • Pal NR, Bezdek JC, Hathaway R (1996) Sequential competitive learning and the fuzzy c-means clustering algorithms. Neural Networks 9:787–796

    Article  Google Scholar 

  • 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

    Article  MathSciNet  Google Scholar 

  • 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

    Article  MATH  Google Scholar 

  • Tsao ECK, Bezdek JC, Pal NR (1994) Fuzzy Kohonen clustering networks. Patt Recogn 27:757–764

    Article  Google Scholar 

  • Vapnik V (1998) Statistical learning theory. Wiley, New York

    MATH  Google Scholar 

  • Wei LM, Xie WX (2000) Rival checked fuzzy c-means algorithm. Acta Electr Sin 28:63–66

    Google Scholar 

  • Xie Z, Wang S, Chung FL (2008) An enhanced possibilistic c-means clustering algorithm. Soft Computing 12:593–611

    Article  MATH  Google Scholar 

  • Yair E, Zeger K, Gersho A (1992) Competitive learning and soft competition for vector quantization design. IEEE Trans Sign Proc 40:294–309

    Article  Google Scholar 

  • Zadeh LA (1965) Fuzzy sets. Inform Contr 8:338–353

    Article  MATH  MathSciNet  Google Scholar 

Download references

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

  1. Faculty of Technical and Human Sciences, Târgu Mureş, Sapientia University of Transylvania, Şoseaua Sighişoarei 1/C, 547367, Corunca, Romania

    László Szilágyi & Sándor M. Szilágyi

  2. Department of Control Engineering and Information Technology, Budapest University of Technology and Economics, Magyar tudósok krt. 2, 1117, Budapest, Hungary

    László Szilágyi & Zoltán Benyó

Authors
  1. László Szilágyi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sándor M. Szilágyi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zoltán Benyó
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to László Szilágyi.

Rights and permissions

Reprints 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

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-009-0452-y

Keywords

Search

Navigation