A Study on Weighting Training Patterns for Fuzzy Rule-Based Classification Systems

  • Tomoharu Nakashima
  • Hisao Ishibuchi
  • Andrzej Bargiela
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3131)


In this paper, we examine the effect of weighting training patterns on the performance of fuzzy rule-based classification systems. A weight is assigned to each given pattern based on the class distribution of its neighboring given patterns. The values of weights are determined proportionally by the number of neighboring patterns from the same class. Large values are assigned to given patterns with many patterns from the same class. Patterns with small weights are not considered in the generation of fuzzy rule-based classification systems. That is, fuzzy if-then rules are generated from only patterns with large weights. These procedures can be viewed as preprocessing in pattern classification. The effect of weighting is examined for an artificial data set and several real-world data sets.


Neighborhood Size Generalization Ability Training Pattern Unseen Data Weight Assignment 
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.
    Sugeno, M.: An Introductory Survey of Fuzzy Control. Information Science 30(1/2), 59–83 (1985)CrossRefMathSciNetGoogle Scholar
  2. 2.
    Lee, C.C.: Fuzzy Logic in Control Systems: Fuzzy Logic Controller Part I and Part II. IEEE Trans. Syst., Man, Cybern. 20, 404–435 (1990)zbMATHCrossRefGoogle Scholar
  3. 3.
    Leondes, C.T. (ed.): Fuzzy theory Systems: Techniques and Applications, vol. 1-4. Academic Press, San Diego (1999)zbMATHGoogle Scholar
  4. 4.
    Ishibuchi, H., Nakashima, T.: Performance evaluation of fuzzy classifier systems for multi-dimensional pattern classification problems. IEEE Trans. on Syst., Man, Cybern. Part B 29, 601–618 (1999)CrossRefGoogle Scholar
  5. 5.
    Ishibuchi, H., Nakashima, T.: Improving the performance of fuzzy classifier systems for pattern classification problems with continuous attributes. IEEE Trans. on Industrial Electronics 46(6), 1057–1068 (1999)CrossRefGoogle Scholar
  6. 6.
    Yuan, Y., Zhang, H.: A genetic algorithms for generating fuzzy classification rules. Fuzzy Sets and Systems, Vol 84(1), 1–19 (1996)zbMATHCrossRefGoogle Scholar
  7. 7.
    Klir, G.J., Yuan, B.: Fuzzy Sets and Fuzzy Logic. Prentice-Hall, Englewood Cliffs (1995)zbMATHGoogle Scholar
  8. 8.
    Ishibuchi, H., Nozaki, K., Tanaka, H.: Distributed representation of fuzzy rules and its application to pattern classification. Fuzzy Sets and Systems 52(1), 21–32 (1992)CrossRefGoogle Scholar
  9. 9.
    Ishibuchi, H., Nozaki, K., Yamamoto, N., Tanaka, H.: Selecting fuzzy if-then rules for classification problems using genetic algorithms. IEEE Trans. on Fuzzy Systems 3(3), 260–270 (1995)CrossRefGoogle Scholar
  10. 10.
    Ishibuchi, H., Nakashima, T.: Effect of rule weights in fuzzy rule-based classification systems. IEEE Trans. on Fuzzy Systems. 9(4), 506–515 (2001)CrossRefGoogle Scholar
  11. 11.
    Nozaki, K., Ishibuchi, H., Tanaka, H.: Adaptive fuzzy rule-based classification systems. IEEE Trans. on Fuzzy Systems 4(3), 238–250 (1996)CrossRefGoogle Scholar
  12. 12.
    Fisher, R.A.: The use of multiple measurements in taxonomic problems. Ann. of Eugenics 7, 179–188 (1936)Google Scholar
  13. 13.
    Weiss, S.M., Kulikowski, C.A.: Computer systems that learn. Morgan Kaufmann, San Mateo (1991)Google Scholar
  14. 14.
    Grabisch, M., Dispot, F.: A comparison of some methods of fuzzy classification on real data. In: Proc. of 2nd Intl. Conf. on Fuzzy Logic and Neural Networks, pp. 659–662 (1992)Google Scholar
  15. 15.
    Grabisch, M.: The representation of importance and interaction of features by fuzzy measures. Pattern Recognition Lett. 17, 567–575 (1996)CrossRefGoogle Scholar
  16. 16.
    Grabisch, M., Nicolas, J.-M.: Classification by fuzzy integral: performance and tests. Fuzzy Sets and Systems 65(2/3), 255–271 (1994)CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Tomoharu Nakashima
    • 1
  • Hisao Ishibuchi
    • 1
  • Andrzej Bargiela
    • 2
  1. 1.Department of Industrial EngineeringOsaka Prefecture UniversitySakai, OsakaJapan
  2. 2.Department of ComputingThe Nottingham Trent UniversityNottinghamUK

Personalised recommendations