Paper:

# An Objective Approach for Constructing a Membership Function Based on Fuzzy Harvda-Charvat Entropy and Mathematical Programming

## Takashi Hasuike^{*} and Hideki Katagiri^{**}

^{*}Faculty of Science and Technology, Waseda University

3-4-1 Okubo, Shinjuku-ku, Tokyo 169-8555, Japan

^{**}Faculty of Engineering, Kanagawa University

3-27-1 Rokkakubashi, Kanagawa-ku, Yokohama, Kanagawa 221-8686, Japan

This paper proposes an objective approach to the construction of an appropriate membership function that extends to our previous studies. It is important to set a membership function with subjectivity and objectivity to obtain a reasonable optimal solution that complies with the decision maker’s feelings in real-world decision making. To ensure objectivity and subjectivity of the obtained membership function, an entropy-based approach based on mathematical programming is integrated into the interval estimation considered by the decision maker. Fuzzy Harvda-Charvat entropy, which is a natural extension of fuzzy Shannon entropy, is introduced as general entropy with fuzziness. The main steps of our proposed approach are to set intervals with membership values 0 and 1 to enable a decision maker to judge confidently, and to solve the proposed mathematical programming problem strictly using nonlinear programming. In this paper, the given membership function is assumed to be a piecewise linear membership function as an approximation of nonlinear functions, and each intermediate value of partial linear function is optimally obtained.

- [1] S. Gottwald, “A note on measures of fuzziness,” Elektron Informationsverarb Kybernet, Vol.15, pp. 221-223, 1979.
- [2] B. Bharathi and V.V.S. Sarma, “Estimation of fuzzy membership from histograms,” Information Sciences, Vol.35, pp. 43-59, 1985.
- [3] M. R. Civanlar and H. J. Trussell, “Constructing membership functions using statistical data,” Fuzzy Sets and Systems, Vol.18, pp. 1-13, 1986.
- [4] H. D. Cheng and Y. H. Cheng, “Thresholding based on fuzzy partition of 2D histogram,” Proc. of IEEE Int. Conf. on Pattern Recognition, Vol.2, pp. 1616-1618, 1997.
- [5] G. Nieradka and B. Butkiewicz, “A method for automatic membership function estimation based on fuzzy measures,” Proc. of IFSA2007, LNAI4529, pp. 451-460, 2007.
- [6] H.D. Cheng and J.R. Cheng, “Automatically determine the membership function based on the maximum entropy principle,” Information Sciences, Vol.96, pp. 163-182, 1997.
- [7] T. Hasuike, H. Katagiri, and H. Tsubaki, “Constructing an appropriate membership function integrating fuzzy Shannon entropy and human’s interval estimation,” ICIC Express Letters, Vol.8, No.3, pp. 809-813, 2014.
- [8] J.L. Chameau and J.C. Santamarina, “Membership function I: Comparing methods of Measurement,” Int. J. of Approximate Reasoning, Vol.1, pp. 287-301, 1987.
- [9] A. Yoshikawa, “Influence of procedure for interacive identification method on forms of identified membership functions,” Japan Society for Fuzzy Theory and Intelligent Informatices, Vol.19, No.1, pp. 69-78, 2007 (in Japanese).
- [10] T. Hasuike, H. Katagiri, and H. Tsubaki, “A constructing algorithm for appropriate piecewise linear membership function based on statistics and information theory,” Procedia Computer Science, Vol.60, pp. 994-1003, 2015.
- [11] K. Fujimoto and M. Sugeno, “Obtaining admissible preference orders using hierarchical bipolar Sugeno and Choquet integrals,” J. of Advanced Computational Intelligence and Intelligent Informatics (JACIII), Vol.17, No.4, pp. 493-503, 2013.
- [12] K. Hayashi, A. Otsumo, and K. Shiranita, “Fuzzy control using piecewise linear membership functions based on knowledge of tuning a PID Controller,” J. of Advanced Computational Intelligence and Intelligent Informatics (JACIII), Vol.5, No.1, pp. 71-77, 2001.
- [13] T. Hasuike, H. Katagiri, and H. Tsubaki, “An interactive algorithm to construct an appropriate nonlinear membership function using information theory and statistical method,” Procedia Computer Science, Vol.61, pp. 32-37, 2015.
- [14] J.H. Havrada and F. Charvat, “Quantification method of classification process: Concept of structural α-entropy,” Kybernetika, Vol.3, pp. 30-35, 1967.
- [15] S. Kumar and A. Choudhary, “Some coding theorems on generalized Havrda-Charvat and Tsallis’s entropy,” Tamkang J. of Mathematics, Vol.43, No.3, pp. 437-444, 2012.
- [16] C. Tsallis, “Possible generalization of Boltzmann-Gibbs statistics,” J. of Statistical Physics, 52, 1988.
- [17] R.K. Bajaj and D.S. Hooda, “On some new generalized measures of fuzzy information,” World Academy of Science, Engineering and Technology, Vol.38, pp. 747-753, 2010.
- [18] A. Kumar, S. Mahajan, and R. Kumar, “Some generalized measures of fuzzy entropy,” Int. J. of Mathematical Sciences and Applications, Vol.1, No.2, pp. 821-829, 2011.
- [19] T. Kumar, R.K. Bajaj, and N. Gupta, “On some parametric generalized measures of fuzzy information, directed divergence and information improvement,” Int. J. of Computer Applications, Vol.30, No.9, pp. 5-10, 2011.
- [20] S. Al-sharhan, F. Karray, and O. Basir, “Fuzzy entropy: a brief survey,” Proc. of FUZZ-IEEE2001, Vol.3, pp. 1135-1138, 2001.
- [21] N.R. Pal and J.C. Bezdek, “Measuring fuzzy uncertainty,” IEEE Trans. on Fuzzy Systems, Vol.2, No.2, pp. 107-118, 1994.