Advertisement

Modified Quick Fuzzy Hypersphere Neural Network for Pattern Classification Using Supervised Clustering

  • D. T. Mane
  • J. P. Kshirsagar
  • U. V. Kulkarni
Conference paper
  • 17 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1118)

Abstract

Defining methods which map the features present in the input to a binomial class output is the core objective of pattern classification. The Modified Quick Fuzzy Hypersphere Neural Network (MQFHSNN) algorithm proposed is an extension of the existing Class-Specific Fuzzy Hypersphere Neural Network (CSFHSNN). Its membership function has been modified such that it outperforms the existing algorithms in the field of pattern classification. Fuzzy set hyperspheres are employed by MQFHSNN for pattern clustering and classes are represented by a combination of fuzzy set hypersphere. By using class labels for forming the clusters, the presented model gives 100% accuracy on the training data. The core contributors to facilitate learning in MQFHSNN are: creation of hyperspheres based on measurements provided by interclass and intraclass distance techniques as well as decision of patterns of individual classes by the fuzzy membership function. The proposed model is put into test on four standard datasets and the results obtained are more superior to the existing models. This leads us to the conclusion that MQFHSNN is being used for improvising model accuracy in pattern classification.

Keywords

Fuzzy hypersphere neural network Pattern classification Supervised clustering 

References

  1. 1.
    Kulkarni, U.V., Sontakke, T.R.: Fuzzy hypersphere neural network classifier. In: IEEE Conference on Fuzzy Systems, pp. 1559–1562. University of Melbourne, Australia (2001)Google Scholar
  2. 2.
    Simpson, P.K.: Fuzzy min-max neural networks. I. Classification. IEEE Trans. Neural Netw. 3(5), 776–786 (1992)CrossRefGoogle Scholar
  3. 3.
    Simpson, P.K.: Fuzzy min-max neural networkPart 2: clustering. IEEE Trans. Fuzzy Syst. 1(1), 32–45 (1993)CrossRefGoogle Scholar
  4. 4.
    Sonar, D.N., Kulkarni, U.V.: Pruned Fuzzy Hypersphere Neural Network (PFHSNN) for lung cancer classification. Int. J. Comput. Appl. 157(7), 36–39 (2017)Google Scholar
  5. 5.
    Kulkarni, A.B., Bonde, S.U., Kulkarni, U.V.: Inter-class and intra-class fuzzy clustering with pruning algorithm. Int. J. Comput. Sci. Eng. 6(5), 94–99 (2018)Google Scholar
  6. 6.
    Mohammed, M.F., Lim, C.P.: An enhanced fuzzy min-max neural network for pattern classification. IEEE Trans. Neural Netw. Learn. Syst. 26(3), 417–429 (2015)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Kulkarni, U.V., Doye, D.D., Sontakke, T.R.: General fuzzy hypersphere neural network. In: International Joint Conference on Neural Network, Honolulu, HI, USA, USA, vol. 3, pp. 2369–2374 (2002)Google Scholar
  8. 8.
    Doye, D.D., Kulkarni, U.V., Sontakke, T.R.: Speech recognition using modified fuzzy hypersphere neural network. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN02), Honolulu, Hawaii , vol. 1, pp. 65–68 (2002)Google Scholar
  9. 9.
    Kulkarni, U.V., Sontakke, T.R.: Fuzzy hypersphere neural network classifier. In: 10th IEEE International Conference on Fuzzy Systems, Melbourne, Victoria, Australia, pp. 1559–1562 (2001)Google Scholar
  10. 10.
    Kondekar, M.H., Kulkarni, U.V., Chowhan, S.S.: Fingerprint recognition using extended fuzzy hypersphere neural network. J. Comput. 3(4), 101–105 (2011)Google Scholar
  11. 11.
    Chowhan, S.S., Kulkarni, U.V., Shinde, G.N.: Iris recognition using modified fuzzy hypersphere neural network with different distance measures. Int. J. Adv. Comput. Sci. Appl. 2(6), 130–134 (2011)Google Scholar
  12. 12.
    Kulkarni, A.B., Bonde, S.V., Kulkarni, U.V.: Class-specific fuzzy hypersphere neural network. Proc. Comput. Sci. 143, 285–294 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • D. T. Mane
    • 1
  • J. P. Kshirsagar
    • 2
  • U. V. Kulkarni
    • 1
  1. 1.Department of Computer Science & EngineeringS. G. G. S. I. E. & T.NandedIndia
  2. 2.Department of Computer EngineeringRajarshi Shahu College of EngineeringPuneIndia

Personalised recommendations