A two-phase approach to fuzzy system identification

Abstract

A two-phase approach to fuzzy system identification is proposed. The first phase produces a baseline design to identify a prototype fuzzy system for a target system from a collection of input-output data pairs. It uses two easily implemented clustering techniques: the subtractive clustering method and the fuzzy c-means (FCM) clustering algorithm. The second phase (fine tuning) is executed to adjust the parameters identified in the baseline design. This phase uses the steepest descent and recursive least-squares estimation methods. The proposed approach is validated by applying it to both a function approximation type of problem and a classification type of problem. An analysis of the learning behavior of the proposed approach for the two test problems is conducted for further confirmation.

Keywords

Fuzzy inference systems / fuzzy system models / fuzzy clustering / learning

References

[1] Bezdek J. C.. Pattern Recognition with Fuzzy Objective Function Algorithm, 1981, New York: Plenum Press

[2] Chen J.-Q., Xi Y.-G., Zhang Z.-J.. A clustering algorithm for fuzzy model identification. Fuzzy Sets and Systems, 1998, 98: 319-329.

[3] Chiu S. L.. Fuzzy model identification based on cluster estimation. Journal of Intelligent and Fuzzy Systems, 1994, 2: 267-278.

[4] Cordón O., Herrera F., Lozano M.. Pedrycz W.. On the combination of fuzzy logic and evolutionary computation: a short review and bibliography. Fuzzy Evolutionary Computation, 1997, Boston: Kluwer Academic Publishers 33-56.

[5] Delgado M., González A.. An inductive learning procedure to identify fuzzy systems. Fuzzy Sets and Systems, 1993, 55: 121-132.

[6] Delgado M., Gómez-Skarmeta, Antonio F., Martín F.. A fuzzy clustering-based rapid prototyping for fuzzy rule-based modeling. IEEE Transactions on Fuzzy Systems, 1997, 5: 223-232.

[7] Fisher R.. The use of multiple measurements in taxonomic problems. Ann. Eugenics, 1936, 7: 179-188.

[8] Fletcher R.. Practical Methods of Optimization, 1993, New York: John Wiley & Sons, Ltd.

[9] Hall, L. O. and P. Lande, “Generating fuzzy rules from data,” in Proceedings of IEEE International Conference on Fuzzy Systems, Piscataway, New Jersey, pp1757–1762, 1996.

[10] Hayashi I., Nomura H., Yamasaki H., Wakami N.. Construction of fuzzy inference rules by NDF and NDFL. International Journal of Approximate Reasoning, 1992, 6: 241-266.

[11] Hong T.-P., Lee C.-Y.. Induction of fuzzy rules and membership functions from training examples. Fuzzy Sets and Systems, 1996, 84: 33-47.

[12] Ishibuchi H.. Pedrycz W.. Development of fuzzy neural networks. Fuzzy Modeling Paradigms and Practice, 1996, Boston: Kluwer Academic Publishers 185-202.

[13] Jang J.-S. R., Sun C.-T., Mizutani E.. Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, 1997, Upper Saddle River: Prentice-Hall, Inc.

[14] Kim E., Park M., Ji S., Park M.. A new approach to fuzzy modeling. IEEE Transactions on Fuzzy Systems, 1997, 5: 328-337.

[15] Liao, Y., “A neural network approach to solve the truck backer-upper and Iris flower classification problems,” working paper, Department of Industrial Engineering, North Carolina State University, 1999.

[16] Lin C.-T., Lin C.-J., Lee C. S. G.. Fuzzy adaptive learning control network with on-line neural learning. Fuzzy Sets and Systems, 1995, 71: 25-45.

[17] Nauck D., Kruse R.. A neuro-fuzzy method to learn fuzzy classification rules from data. Fuzzy Sets and Systems, 1997, 89: 277-288.

[18] Nomura, H., I. Hayashi, and N. Wakami, “A learning method of fuzzy inference rules by descent method,” in Proceedings of IEEE International Conference on Fuzzy Systems, San Diego, Los Angeles, pp203–210, 1992.

[19] Strobach P.. Linear Prediction Theory: A Mathematical Basis for Adaptive Systems, 1990, New York: Springer-Verlag

[20] Sugeno M., Yasukawa T.. A fuzzy-logic-based approach to qualitative modeling. IEEE Transactions on Fuzzy Systems, 1993, 1: 7-31.

[21] Takagi T., Sugeno M.. Fuzzy identification of systems and its application to modeling and control. IEEE Transactions on Systems, Man, and Cybernetics, 1985, SMC-15: 116-132.

[22] Thoney, K., “A fuzzy truck backer-upper problem with a barrier,” NSCU-IE/OR Course 591F Project, North Carolina State University, 1997.

[23] Wang H.-F., Wang C., Wu G.-Y.. Bi-criteria fuzzy c-means analysis. Fuzzy Sets and Systems, 1994, 64: 311-319.

[24] Wang L.-X., Mendel J. M.. Generating fuzzy rules by learning from examples. IEEE Transactions on Systems, Man, and Cybernetics, 1992, 22: 1414-1427.

[25] Wang L.-X.. A Course in Fuzzy Systems and Control, 1997, New Jersey: Prentice-Hall, Inc.

[26] Zadeh L. A.. Klir G. J.. From circuit theory to system theory. Facets of Systems Science, 1991, New York: Plenum Press 309-323.