A neuro-fuzzy architecture for high performance classification

  • Sung-Bae Cho
Fuzzy — Neural Networks
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1011)


The concept of combining modular neural networks has been recently exploited as a new direction for the development of highly reliable neural network systems in the area of pattern classification. In this paper we present an efficient method for combining the modular networks based on fuzzy logic, especially the fuzzy integral. This method nonlinearly combines objective evidences, in the form of network outputs, with subjective evaluation of the reliability of the individual neural networks. Also, for more effective aggregation, we adopt the extension of the fuzzy integral with ordered weighted averaging operators. The experimental results with the recognition problem of on-line handwriting characters show that the performance of individual networks could be improved significantly.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hansen, L.K., Salamon, P.: Neural network ensembles. IEEE Trans. Patt. Anal. Mach. Inte. 12 (1990) 993–1001Google Scholar
  2. 2.
    Scofield, C., Kenton, L., Chang, J.: Multiple neural net architectures for character recognition. Proc. Compcon. (1991) 487–491 (San Francisco, CA, IEEE Computer Society Press)Google Scholar
  3. 3.
    Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comp. 3 (1991) 79–87Google Scholar
  4. 4.
    Wolpert, D.: Stacked generalization. Neural Net. 5 (1992) 241–259Google Scholar
  5. 5.
    Cho, S.-B., Kim, J.H.: Two design strategies of neural network for complex classification problems. Proc. 2nd Int. Conf. Fuzzy Logic & Neural Net. (1992) 759–762Google Scholar
  6. 6.
    Perrone, M.P., Cooper, L.N.: When networks disagree: Ensemble methods for hybrid neural networks. Neural Net. for Speech and Image Proc. (1993) (Mammone, R.J. ed., Chapman-Hill, London)Google Scholar
  7. 7.
    Hampshire, J.B. II, Waibel, A.: Connectionist architectures for multi-speaker phoneme recognition. Adv. Neural Info. Proc. Syst 2 (1990) 203–210Google Scholar
  8. 8.
    Xu, L., Krzyzak, A., Suen, C.Y.: Methods of combining multiple classifiers and their applications to handwriting recognition. IEEE Trans. Syst. Man. Cyber. 22 (1992) 688–704Google Scholar
  9. 9.
    Benediktsson, J.A., Swain, P.H.: Consensus theoretic classification methods. IEEE Trans. Syst. Man. Cyber. 22 (1992) 418–435Google Scholar
  10. 10.
    Cho, S.-B., Kim, J.H.: Combining multiple neural networks by fuzzy integral for robust classification. IEEE Trans. Syst. Man. Cyber. 25 (1995) 380–384Google Scholar
  11. 11.
    Richard, M.D., Lippmann, R.P.: Neural network classifiers estimate Bayesian a posteriori probabilities. Neural Comp. 3 (1991) 461–483Google Scholar
  12. 12.
    Shlien, S.: Multiple binary decision tree classifiers. Patt. Recog. 23 (1990) 757–763Google Scholar
  13. 13.
    Sugeno, M.: Fuzzy measures and fuzzy integrals: A survey. Fuzzy Automata Dec. Proc. (1977) 89–102 (Amsterdam: North Holland)Google Scholar
  14. 14.
    Leszeynski, K., Penczek, P., Grochulskki, W.: Sugeno's fuzzy measures and fuzzy clustering. Fuzzy Sets Syst. 15 (1985) 147–158Google Scholar
  15. 15.
    Tahani, H., Keller, J.M.: Information fusion in computer vision using the fuzzy integral. IEEE Trans. Syst. Man. Cyber. 20 (1990) 733–741Google Scholar
  16. 16.
    Yager, R.R.: Element selection from a fuzzy subset using the fuzzy integral. IEEE Trans. Syst. Man. Cyber. 23 (1993) 467–477Google Scholar
  17. 17.
    Yager, R.R.: On ordered weighted averaging aggregation operators in multicriteria decisionmaking. IEEE Trans. Syst. Man. Cyber. 18 (1988) 183–190Google Scholar
  18. 18.
    Tappert, C.C., Suen, C.Y., Wakahara, T.: The state of the art in on-line handwriting recognition. IEEE Trans. Patt. Anal. Mach. Intel. 12 (1990) 787–808Google Scholar
  19. 19.
    Freeman, H.: Computer processing in line drawing images. Comp. Surv. 6 (1974) 57–98Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Sung-Bae Cho
    • 1
  1. 1.Department of Computer ScienceYonsei UniversitySudaemoon-ku, SeoulKorea

Personalised recommendations