Soft Techniques for Bayesian Classification

  • Robert Nowicki
  • Leszek Rutkowski
Part of the Advances in Soft Computing book series (AINSC, volume 19)


In this paper we present a neuro-fuzzy classifier performing a Bayes decision function. The classifier is based on a neuro-fuzzy structure. The rough set theory is incorporated into this structure. It will be shown that a new hybrid system, i.e. rough-neuro-fuzzy classifier, is able to perform classification in the case of missing features.


Membership Function Soft Computing Soft Computing Technique Fuzzy Classification BAYESIAN Classification 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    V. Kecman, “Learning and Soft Computing”, MIT, Cambridge, 2001.Google Scholar
  2. [2]
    L. I. Kuncheva, “On the Equivalence Between Fuzzy and Statistical Classifiers”, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, Vol. 4, No. 3, 1996, pp. 245–253.MathSciNetMATHCrossRefGoogle Scholar
  3. [3]
    R. Nowicki, L. Rutkowski, “Rough-Neuro-Fuzzy System For Classification”, Proc. of FSKD’02 Singapure, 2002.Google Scholar
  4. [4]
    E. Parzen, “On estimation of a probability density function”, Annals of Math. Statistics, Vol. 33, pp. 1065–1076.Google Scholar
  5. [5]
    Z. Pawlak, „Rough sets“, International Journal of Information and Computer Science, Vol. 11, No. 341, 1982.Google Scholar
  6. [6]
    D. Rutkowska, R. Nowicki, „New neuro-fuzzy architectures“, Proc. Int. Conf. on Artificial and Computational Intelligence for Decision, Control and Automation in Engineering and Industrial Applications, ACIDCA’2000, Intelligent Methods, Monastir, Tunisia, March, 2000, pp. 82–87.Google Scholar
  7. [7]
    D. Rutkowska, R. Nowicki, L. Rutkowski, “Neuro-fuzzy architectures with various implication operators”, The State of the Art in Computational Intelligence–Proc. Intern. Symposium on Computational Intelligence (ISCI 2000), Springer-Verlag, Kosice, Slovakia, August/September 2000, pp. 214–219.Google Scholar
  8. [8]
    D. Rutkowska and R. Nowicki, “Implication — based neuro-fuzzy architectures”, International Journal of Applied Mathematics and Computer Science, No. 4, 2000, pp. 675–701.Google Scholar
  9. [9]
    L. Rutkowski, “Identification of MISO non-linear regressions in the presence of a wide class of disturbances”, IEEE Trans. Information Theory, Vol. IT37, 1991, pp. 214–216.Google Scholar
  10. [10]
    L. Rutkowski, Multiple Fourier series procedures of non-linear regressions from noisy data. — IEEE Trans. Signal Processing, Vol. 41, No. 10, 1993, pp. 109–118.CrossRefGoogle Scholar
  11. [11]
    L. Rutkowski, “New Soft Computing Techniques For System Modelling, Pattern Classification and Image Processing”, Springer-Verlag (to be published).Google Scholar
  12. [12]
    L. Rutkowski, K. Cpalka, „Flexible Neuro-Fuzzy Systems“, IEEE Trans. Neural Networks, (submitted for publication).Google Scholar
  13. [13]
    L.-X. Wang, “Adaptive Fuzzy Systems and Control”, PTR Prentice Hall, Englewood Cliffs, New Jersey, 1994.Google Scholar
  14. [14]
    L. A. Zadeh, New Frontiers in Fuzzy Logic and Soft Computing, Proc. of Fourth Conference „Neural Networks and Their Application“, Zakopane, May 18–22, 1999, pp. 1–4.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Robert Nowicki
    • 1
  • Leszek Rutkowski
    • 1
  1. 1.Department of Computer EngineeringTechnical University of CzestochowaCzęstochowaPoland

Personalised recommendations