Fuzzy Model Identification Based on Rough Set Data Analysis
It is an open problem to model nonlinear systems with uncertainties. In Chapter 2, we developed an identification algorithm based on the Takagi-Sugeno fuzzy model. The fuzzy modeling procedure in Chapter 2 can be divided into three steps: premise structure identification, premise parameters identification, and consequent parameters identification. The premise structure identification procedure is done in two phases: (1) Identify the input structure, i.e., the significant input variables are identified among all possible input candidates; (2) assign fuzzy membership functions. In Chapter 2, we introduced an identification algorithm which included both phases in a uniform processes. We can also deal with them in two individual processes.
KeywordsArtificial Neural Network Artificial Neural Network Modeling Fuzzy Rule Fuzzy Model Fuzzy Membership Function
Unable to display preview. Download preview PDF.
- M. Arima, E. H. Hara, and J. D. Katzberg, “Fuzzy logic and rough sets controller for HAVC systems,” Proceedings of IEEE WESCANEX 95 Conference on Communications, Power, and Computing, Winnipeg, Manitoba, Canada, May 1995, pp. 133–138.Google Scholar
- X. Feng, K. Katsuyama, and Y. Wang, “Self-learning based and adaptive modeling on estimation of rock slope stability,” Journal of the Mining and Materials Processing Institute of Japan, vol. 112, pp. 851–858, 1996.Google Scholar
- F. Hoppner, F. Klawonn, R. Kruse, and T. Runkler, Fuzzy Cluster Analysis: Methods for Classification. Data Analysis and Image Recognition, New York: John Wiley, 1999.Google Scholar
- M. Li and H. Zhang, “Nonlinear system input structure identification based on rough set data analysis,” Proceedings of the 10th IEEE International Conference on Fuzzy Systems, Melbourne, Australia, Dec. 2001, pp. 300–303.Google Scholar
- M. Li and H. Zhang, “Identification of fuzzy model based on rough sets theory,” Journal of Northeastern University, vol. 21, no. 5, pp. 480–483, Oct. 2000 (in Chinese).Google Scholar
- M. Li and H. Zhang, “Research on the method of neural network modeling based on rough sets theory,” ACTA Automatica Sinica, vol. 28, no. 1, pp. 27–33, Jan. 2002 (in Chinese).Google Scholar
- Y. Lin and G. A. Cunningham III, “Building a fuzzy systems from input-output data,” Journal of Intelligent & Fuzzy System, vol. 2, pp. 243–250, 1994.Google Scholar
- P. Chen and T. Toyota, “Multivalued neural network and the knowledge acquisition method by the rough sets for ambiguous recognition problem,” Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, Beijing, China, Oct. 1996, pp. 736–740.Google Scholar
- M. Sarkar and B. Yegnanarayana, “Application of fuzzy-rough sets in modular neural networks,” Proceedings of IEEE International Joint Conference on Neural Networks, Anchorage, AK, Aug. 1998, pp. 741–746.Google Scholar