Kernel-Based Fuzzy C-Means Clustering Algorithm for RBF Network Initialization

  • Ireneusz CzarnowskiEmail author
  • Piotr Jędrzejowicz
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 56)


Designing an effective structure of the RBF network is the task carried-out at the network initialization phase. Usual approach to deal with the problem is to decide on the number of hidden units and to apply a clustering algorithm to calculate cluster centroids. Clustering techniques have a strong influence on the performance of the RBF networks. The paper focuses on the radial basis function neural network initialization problem and the implementation of the kernel-based fuzzy C-means clustering algorithm, as an alternative method for the RBF networks initialization. Performance of the RBFNs initialized using the kernel-based fuzzy clustering algorithm is compared with several other clustering techniques, including k-means, fuzzy C-means and X-means.


Classification Neural networks Radial basis function Clustering Kernel-based clustering 


  1. 1.
    Asuncion, A., Newman, D.J.: UCI Machine Learning Repository. University of California, School of Information and Computer Science, Irvine (2007)
  2. 2.
    Bezdek, J.C.: Pattern Recognition with Fuzzy Objective Function Algorithms. Springer Publishers, New York (1981)CrossRefzbMATHGoogle Scholar
  3. 3.
    Broomhead, D.S., Lowe, D.: Multivariable Functional Interpolation and Adaptive Networks. Complex Syst. 2, 321–355 (1988)MathSciNetzbMATHGoogle Scholar
  4. 4.
    Chen, H., Gong, Y., Hong, X., Chen. S.: A Fast Adaptive Tunable RBF Network for Non-stationary Systems. IEEE Trans. Syst. Man Cybern. Part B (99), 1–10 (2015). doi: 10.1109/TCYB.2015.2484378 Google Scholar
  5. 5.
    Chen, S., Billings, S.A., Grant, P.M.: Recursive hybrid algorithm for non-linear system identification using radial basis function networks. Int. J. Control 55(5), 1051–1070 (1992). doi: 10.1080/00207179208934272 MathSciNetCrossRefzbMATHGoogle Scholar
  6. 6.
    Czarnowski, I., Jędrzejowicz, P.: Agent-based approach to the design of RBF networks. Cybern. Syst. 44(2–3), 155–172 (2013)CrossRefGoogle Scholar
  7. 7.
    Czarnowski, I., Jędrzejowicz, J., Jędrzejowicz, P.: Designing RBFNs with similarity-based and kernel-based fuzzy C-means clustering algorithm. ACM Trans. Knowl. Discov. Data 2016 (manuscript submitted for publication)Google Scholar
  8. 8.
    De Corvalho, A., Brizzotti, M.M.: Combining RBF networks trained by different clustering techniques. Neural Process. Lett. 14, 227–240 (2001)Google Scholar
  9. 9.
    Du, K.-L.: Clustering: A neural network approach. J. Neural Netw. 23(1), 89–107 (2010). doi: 10.1016/j.neunet.2009.08.007 CrossRefGoogle Scholar
  10. 10.
    Gao, H., Feng, B., Zhu, L.: Training RBF neural network with hybrid particle swarm optimisation. In: Weng, J., et al. (eds.) ISNN 2006, LNCS 3971, pp. 577–583. Springer, Berlin Heidelberg (2006)Google Scholar
  11. 11.
    Garg, S., Patra, K., Khetrapal, V., Pal, S.K., Chakraborty, D.: Genetically evolved radial basis function network based prediction of drill flank wear. Eng. Appl. Artif. Intell. 23, 1112–1120 (2010)CrossRefGoogle Scholar
  12. 12.
    Graves, D., Pedrycz, W.: Kernel-based fuzzy clustering and fuzzy clustering: a comparative experimental study. Fuzzy Sets Syst. 161, 522–543 (2010). doi: 10.1016/j.fss.2009.10.021 MathSciNetCrossRefGoogle Scholar
  13. 13.
    Grover, N.: A study of various fuzzy clustering algorithms. Int. J. Eng. Res. 3(3), 177–181 (2014)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Havens, T.C., Bezdek, J.C., Palaniswami, M.: Cluster validity for kernel fuzzy clustering. In: Proceedings of 2012 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). IEEE. Brisbane, QLD, pp. 1–8 (2012). doi: 10.1109/FUZZ-IEEE.2012.6250820
  15. 15.
    Huang, G.-B., Saratchandra, P., Sundararajan, N.: A generalized growing and pruning RBF(GGAP-RBF) neural network for function approximation. IEEE Trans. Neural Netw. 16(1), 57–67 (2005). doi: 10.1109/TNN.2004.836241 CrossRefGoogle Scholar
  16. 16.
    Krishnaiah, P.R., Kanal, L.N.: Handbook of Statistics 2: Classification, Pattern Recognition and Reduction of Dimensionality. North Holland, Amsterdam (1982)Google Scholar
  17. 17.
    Li, Z., Tang, S., Xue, J., Jiang, J.: Modified FCM clustering based on kernel mapping. In: Proceedings of the International Conference on Society for Optical Engineering, vol. 4554, pp. 241–245 (2001). doi: 10.1117/12.441658
  18. 18.
    Mashor, M.Y.: Hybrid training algorithm for RBF network. Int. J. Comput. Internet Manag. 8(2), 50–65 (2000)Google Scholar
  19. 19.
    Mekhmoukh, A., Mokrani, K., Cheriet, M.: A modified Kernelized Fuzzy C-Means algorithm for noisy images segmentation: application to MRI images. IJCSI Int. J. Comput. Sci. Issues 9(1), 1172–1176 (2012)Google Scholar
  20. 20.
    Moody, J., Darken, C.J.: Fast learning in networks of locally-tuned processing units. Neural Comput. 1(2), 281–294 (1989)CrossRefGoogle Scholar
  21. 21.
    Niros, A.D., Tsekouras, G.E.: A novel training algorithm for RBF neural network using a hybrid fuzzy clustering approach. J. Fuzzy Sets Syst. 193, 62–84 (2012). doi: 10.1016/j.fss.2011.08.011 MathSciNetCrossRefGoogle Scholar
  22. 22.
    Pelleg, D., Moore, A.: X-means: Extending K-means with efficient estimation of the number of clusters. In: Proceedings of the Seventeenth International Conference on Machine Learning, pp. 727–734 (2000)Google Scholar
  23. 23.
    Platt, J.C.: A resource-allocating network for function interpolation. Neural Comput. 3(2), 213–225 (1991)MathSciNetCrossRefGoogle Scholar
  24. 24.
    Ruspini, E.H.: Numerical methods for fuzzy clustering. J. Inf. Sci. 2(3), 319–350 (1970)CrossRefzbMATHGoogle Scholar
  25. 25.
    Sánchez, A.V.D.: Searching for a solution to the automatic RBF network design problem. Neurocomputing 42(1–4), 147–170 (2002)CrossRefzbMATHGoogle Scholar
  26. 26.
    Wong, Y.W., Seng, K.P., Ang, L.-M.: Radial basis function neural network with incremental learning for face recognition. IEEE Trans. Syst. Man Cybern. Part B—Cybern. 41(4), 1–16 (2011). doi: 10.1109/TSMCB.2010.2101591 Google Scholar
  27. 27.
    Zhou, S., Gan, J.Q.: Mercel kernel fuzzy c-means algorithm and prototypes of clusters, In: Proceedings of the International Conference on Data Engineering and Automated Learning. Lecture Notes in Computer Science, vol. 3177, pp. 613–618 (2004). doi: 10.1007/978-3-540-28651-6_90 Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Department of Information SystemsGdynia Maritime UniversityGdyniaPoland

Personalised recommendations