A new fuzzy set merging technique using inclusion-based fuzzy clustering

Article English OPEN
Nefti-Meziani, S ; Kaymak, U ; Oussalah, M
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • Related identifiers: doi: 10.1109/TFUZZ.2007.902011
  • Subject: other | QA75
    acm: ComputingMethodologies_PATTERNRECOGNITION

This paper proposes a new method of merging parameterized fuzzy sets based on clustering in the parameters space, taking into account the degree of inclusion of each fuzzy set in the cluster prototypes. The merger method is applied to fuzzy rule base simplification by automatically replacing the fuzzy sets corresponding to a given cluster with that pertaining to cluster prototype. The feasibility and the performance of the proposed method are studied using an application in mobile robot navigation. The results indicate that the proposed merging and rule base simplification approach leads to good navigation performance in the application considered and to fuzzy models that are interpretable by experts. In this paper, we concentrate mainly on fuzzy systems with Gaussian membership functions, but the general approach can also be applied to other parameterized fuzzy sets.
  • References (45)
    45 references, page 1 of 5

    [1] M. Setnes, R. Babusˇka, U. Kaymak, and H. R. van Nauta Lemke, “Similarity measures in fuzzy rule base simplification,” IEEE Trans. Syst., Man, Cybern. B, Cybern., vol. 28, no. 3, pp. 376-386, Jun. 1998.

    [2] S. Guillaume, “Designing fuzzy inference systems from data: An interpretability-oriented review,” IEEE Trans. Fuzzy Syst., vol. 9, no. 3, pp. 426-443, Jun. 2001.

    [3] V. V. Cross, “An analysis of fuzzy set aggregators and compatibility measures,” Ph.D. dissertation, Dept. Comp. Sci. Eng., Wright State Univ., OH, 1993.

    [4] M. Setnes, “Fuzzy rule-base simplification using similarity measures,” M.Sc. thesis, Control Lab., Faculty Electr. Eng., Delft Univ. Technol., Delft, The Netherlands, Jul. 1995.

    [5] R. Zwick, E. Carlstein, and D. V. Budescu, “Measures of similarity among fuzzy concepts: A comparative analysis,” Int. J. Approx. Reason., vol. 1, pp. 221-242, 1987.

    [6] U. Kaymak and M. Setnes, “Fuzzy clustering with volume prototypes and adaptive cluster merging,” IEEE Trans. Fuzzy Syst., vol. 10, no. 6, pp. 705-712, Dec. 2002.

    [7] U. Kaymak and R. Babusˇka, “Compatible cluster merging for fuzzy modelling,” in Proc. 4th IEEE Int. Conf. Fuzzy Syst., Yokohama, Japan, Mar. 1995, vol. 2, pp. 897-904.

    [8] C.-L. Chang, “Finding prototypes for nearest neighbor classifiers,” IEEE Trans. Comput., vol. C-23, no. 11, pp. 1179-1184, Nov. 1974.

    [9] J. C. Bezdek, T. R. Reichherzer, G. S. Lim, and Y. Attikiouzel, “Multiple-prototype classifier design,” IEEE Trans. Syst., Man, Cybern. C, Appl. Rev., vol. 28, no. 1, pp. 67-79, Feb. 1998.

    [10] R. A. Mollineda, F. J. Ferri, and E. Vidal, “An efficient prototype merging strategy for the condensed 1-NN rule through class-conditional hierarchical clustering,” Pattern Recognit., vol. 35, no. 12, pp. 2771-2782, Dec. 2002.

  • Metrics
    No metrics available
Share - Bookmark