On choosing the fuzziness parameter for identifying TS models with multidimensional membership functions

• Autorzy: Kroll A.
• Języki publikacji: EN

Abstrakty

EN

Fuzzy clustering is a well-established method for identifying the structure/fuzzy partitioning of Takagi-Sugeno (TS) fuzzy models. The clustering algorithms require choosing the fuzziness parameter m. Prior work in the area of pattern recognition shows, that a suitable choice of m is application- dependent. Yet, the default of m=2 is commonly chosen. This paper examines the suitable choice of m for identifying TS models. The focus is on models that use the classifiers resulting from fuzzy clustering as multi-dimensional membership functions or their projection and approximation. At first, the differentiability and grouping properties of the fuzzy classifiers are analyzed to make a general recommendation of choosing m(1;3). Besides, the effect of the cluster number c on the classification fuzziness is examined. Finally, requirements that are specific to TS modeling are introduced, which narrow down the suitable range for m. Building on algorithm analysis and four case studies (function approximation, a vehicle engine and an axial compressor application for nonlinear regression), it is demonstrated that choosing m2(1;1.3) for local and m2(1;1.5) for global estimation will typically provide for good results.

Słowa kluczowe

EN

fuzzy clustering; structure/fuzzy partitioning; Takagi-Sugeno fuzzy models; TS fuzzy models; fuzziness parameter m; fuzzy classifier

• Wydawca: University of Social Sciences
• Czasopismo: Journal of Artificial Intelligence and Soft Computing Research
• Rocznik: 2011
• Tom: Vol. 1, No. 4
• Strony: 283--300
• Opis fizyczny: Bibliogr. 51 poz., rys.

Twórcy

autor

Kroll A.

• Measurement and Control Department, Mechanical Engineering, University of Kassel Mnchebergstrasse 7, D-34125 Kassel

Bibliografia

• [1] Takagi T. and Sugeno M., ”Fuzzy identification of systems and its application to modelling and control”, IEEE Trans. Systems, Man and Cybernetics, Vol. 15, No. 1, pages 116–132, 1985.
• [2] Tanaka K. and Wang H.O., Fuzzy Control Systems design and analysis: a linear matrix inequality approach. New York: Wiley, 2001.
• [3] Kawamoto S., Tada K., Ishigame A. and Taniguchi T., ”An approach to stability analysis of second order fuzzy systems,” Proc. IEEE Conf. on Fuzzy Systems, San Diego, pages 1427–1434, 1992.
• [4] Wang H.O., Tanaka K. and Griffin M.F., “An approach to fuzzy control of nonlinear systems: stability and design issues,” IEEE Trans. on Fuzzy Systems, Vol. 4, No. 1, pages 14–23, 1996.
• [5] Johansen T.A., Hunt K.J., Gawthrop P.J. and Fritz H., ”Off-equilibrium linearization and design of gain-scheduled control with application to vehicle speed control,” Control Eng. Practice, Vol. 6, pages 167–180, 1998.
• [6] Nelles O., Nonlinear system identification. Berlin, Germany: Springer, 2001.
• [7] Hartmann B. and Nelles O., “Automatic adjustment of the transition between local models in a hierarchical structure identification algorithm,” in Proc. European Control Conference (ECC’2009), Budapest, Hungary, pages 1599–1604, August 2009.
• [8] Kroll A., “Identification of functional fuzzy models using multidimensional reference fuzzy sets,” Fuzzy Sets and Systems, Vol. 80, No. 2, pages 149–158, 1996.
• [9] Kroll A., “On modeling discontinuous and heterogeneous nonlinear systems using Takagi-Sugeno systems,” (in German) in Proc. GMA Workshop ’Computational Intelligence’, Dortmund, Germany, pages 64–79, Dec. 2010.
• [10] Bezdek J. C., Pattern recognition with fuzzy objective function algorithms, New York: Plenum, 1981.
• [11] Babuska R., Fuzzy modeling for control, Boston: Kluwer, 1998.
• [12] Hppner F., Kruse F., Klawonn F. and Runkler T., Fuzzy cluster analysis, Chichester, England: Wiley, 1999.
• [13] Abonyi J., Fuzzy model identification for control. Berlin: Birkhuser, 2003.
• [14] Krishnapuram R. and Freg C.-P., ”Fitting an unknown number of lines and planes to image data through compatible cluster merging”, Pattern Recognition, Vol. 25, No. 4, pages 385–400, 1992.
• [15] Sin S.-K., and de Figuero R. J. P., “Fuzzy system design through fuzzy clustering and optimal predefuzzification,” in Proc. 2nd IEEE Conf. on Fuzzy Systems, San Francisco, pages 190–195, 1993.
• [16] Laukonen E. G., Passino K. M., Krishnaswami V., Luth G.-C. and Rizzoni G., “Fault detection and isolation for an experimental internal combustion engine via fuzzy identification,” IEEE Trans. Control Systems Technology, Vol. 3, No. 3, pages 347–355, Sep. 1995.
• [17] Setnes M., “Supervised fuzzy clustering for rule extraction”, IEEE Trans. Fuzzy Systems, Vol. 8, No. 4, pages 416–424, August 2000.
• [18] Abonyi J., Babuska R. and Szeifert F., ”Modified Gath-Geva fuzzy clustering for identification of Takagi-Sugeno fuzzy models,” IEEE Trans. Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 32, No. 5, pages 612–621, Oct. 2002.
• [19] Feil B., Abonyi J. and Szeifert F., ”Model order selection of nonlinear input-output models - a clustering based approach,” Journal of Process Control, Vol. 14, pages 593–602, 2004.
• [20] Hwang C. and Rhee F. C.-H., “Uncertain fuzzy clustering: interval type-2 fuzzy approach to cmeans”, IEEE Trans. Fuzzy Systems, Vol. 15, No. 1, pages 107–120, Feb. 2007.
• [21] Yu J., Cheng Q. and Huang H., ”Analysis of the weighting exponent in the FCM”, IEEE Trans. Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 34, No. 1, pages 634–638, Feb. 2004.
• [22] Klawonn F. and Hppner F., “What is fuzzy about fuzzy clustering? Understanding and improving the concept of the fuzzifier,” Proc. 5th Int. Symposium on Intelligent Data Analysis IDA 2003, Berlin, Germany, pages 254–264, Aug. 2003.
• [23] Hathaway R.J. and Bezdek J.C., ”Fuzzy c-means clustering of incomplete data,” IEEE Trans. Systems, Man, and Cybernetics — Part B: Cybernetics, Vol. 31, No. 5, pages 735–744, Oct. 2001.
• [24] Bezdek J.C., Keller J., Krishnapuram R. and Pal N.R., Fuzzy models and algorithms for pattern recognition and image processing, Boston: Kluwer, 1999.
• [25] Dembl D. and Kastner P., ”Fuzzy c-means method for clustering microarray data,” Bioinformatics, Vol. 19, pages 973–980, Aug. 2003.
• [26] Zeinali M. and Notash L., ”A systematic method of adaptive fuzzy logic modeling, using an improved fuzzy c-means clustering algorithm for rule generation,” in Proc. 2005 IEEE Conf. Control Applications, Toronto, Canada, pages 84–89, Aug. 2005.
• [27] Pal N. R., Bezdek J. C., ”On cluster validity for the fuzzy c-means model”, IEEE Trans. Fuzzy Systems, Vol. 3, pages 370–379, Aug. 1995.
• [28] Bernd T., Kroll A. and Schwarz H., ”Approximating nonlinear dynamic processes with optimized functional fuzzy models,” (in German) in Proc. GMA Workshop ‘Fuzzy Control’, Dortmund, Germany, pages 179–190, Nov. 1997.
• [29] Zimmerschied R., “Identifying nonlinear processes with dynamic local-affine models – means to reduce bias and variance,” (in German), Ph.D. Dissertation, Univ. of Darmstadt, July 2008.
• [30] Babuka R., Fantuzzi C., Kaymak U. and Verbruggen H.B., ”Improved inference for Takagi-Sugeno models,” in Proc. 5th IEEE International Conference on Fuzzy Systems, 1996, pages 1642–1647.
• [31] Dunn J. C., ”A fuzzy relative of the isodata process and its use in detecting compact well-separated clusters,” Journal of Cybernetics, Vol. 3, pages 32–57, 1973.
• [32] Zimmerschied R. and Isermann R., “Regularization techniques for identification using local-affine models,” (in German) at – Automatisierungstechnik,Vol. 56, No. 7, pages 339–349, 2008.
• [33] Bezdek J. C., Ehrlich R. and Full W., ”FCM: The fuzzy c-means clustering algorithm,” Computers & Geosciences, Vol. 10, No. 2-3, pages 191–203,1984.
• [34] McBratney A. B. and Moore A. W., ”Application of fuzzy sets to climatic classification,” Agricultural and Forest Meteorology, Vol. 35, No. 1–4,pages 165–185, 1985.
• [35] Choe H. and Jordan J. B., “On the optimal choice of parameters in a fuzzy c-means algorithm,” in Proc. IEEE Int. Conf. on Fuzzy Systems, San Diego, USA, pages 349-354, March 1992.
• [36] Emami M. R., Trksen I. B. and Goldenberg A. A., ”Development of a systematic methodology of fuzzy logic modeling,” IEEE Trans. Fuzzy Systems, Vol. 6, No. 3, pages 346–361, Aug. 1998.
• [37] Chen M. S. and Wang S. W., ”Fuzzy clustering analysis for optimizing fuzzy membership functions,” Fuzzy Sets and Systems, Vol. 103, No. 2, pages 239-254, April 1999.
• [38] Gao X., Lie J. and Xie W., ”Parameter optimization in FCM clustering algorithms,” in Proc. 5th Int. Conf. on Signal Processing Proceedings (WCCCICSP’2000), Vol. 3, pages 1457–1461, 2000.
• [39] Deer P. J.and Eklund P., ”A study of parameter values for a Mahalanobis distance fuzzy classifier,”Fuzzy Sets and Systems, Vol. 137, No. 2, pages 191-213, 2003.
• [40] Mller U., “Missing clusters indicate poor estimates or guesses of a proper fuzzy exponent,” in Applications of Fuzzy Sets Theory. Berlin, Germany: Springer, pages 161–169, 2007.
• [41] YangW., Rueda L. and Ngom A., ”A simulated annealing approach to find the optimal parameters for fuzzy clustering microarray data,” in Proc. 25th Int. Conf. Chilean Computer Science Society, Valdivia, Chile, pages 45–55, 2005.
• [42] Okeke F., Karnieli A., ”Linear mixture model approach for selecting fuzzy exponent value in fuzzy c-means algorithm,” Ecological Informatics, Vol. 1, pages 117–124, Jan. 2006. 300 A. Kroll
• [43] Kung C. C., Su J. Y., ”A study of cluster validity criteria for the fuzzy c-regression models clustering algorithm,” in Proc. 2007 IEEE Int. Conf. Systems, Man and Cybernetics, Montreal, Canada, pages 853–858, Oct. 2007.
• [44] Sugeno M., Yasukawa T., “A fuzzy logic approach to qualitative modeling,” IEEE Trans. Fuzzy Systems, Vol. 1, No. 1, pages 7–31, Feb. 1993.
• [45] Zarandi M. H. F., Esmaeilian M., Zarandi M. M.F., ”A systematic fuzzy modeling for scheduling of textile manufacturing system,” Int. Journal of Management Science and Engineering Management, Vol. 2, No. 4, pages 297–308, 2007.
• [46] Alata M., Molhim M., Ramini A.: ”Optimizing of fuzzy c-means clustering algorithm using GA,” World Academy of Science, Engineering and Technology, Vol. 39, pages 224–229, Mar. 2008.
• [47] Hoppner F., Klawonn F. , ”A new approach to fuzzy partitioning,” in Proc. Joint 9th IFSA World Congr. and 20th NAFIPS Int. Conf., Vancouver, Canada, pages 1419–1424, 2001.
• [48] Kroll A., Soldan S., “On data-driven Takagi-Sugeno modeling of heterogeneous systems with multidimensional membership functions”, in Proc. 18th World Congress of the Int. Federation of Automatic Control (IFAC), Milano, Italy, pages 4803–4808, August 2011.
• [49] Dav R. N. , “Characterization and detection of noise in clustering,” Pattern Recognition Letters, Vol. 12, pages 657–664, 1991.
• [50] Mnz E. , “Identification and diagnosis of hybrid dynamical systems”, (in German) Ph.D. Dissertation, Univ. of Karlsruhe, Universittsverlag Karlsruhe,2006.
• [51] Krishnapuram R., Keller J., ”A possibilistic approach to clustering”, IEEE Trans. Fuzzy Systems, Vol. 1, No. 2, pages 98–110, May 1993