Research of Classification Tasks Solving Using Neural Fuzzy Production Based Network Models of Mamdani–Zadeh

O. P. Soldatova ; I. A. Lyozin

Journal of Samara State Technical University, Ser. Physical and Mathematical Sciences, Tome 135 (2014) no. 2, pp. 136-148

Résumé

The article considers solving the problem of object recognition of intersected classes using fuzzy inference systems and neural networks. New multi-output network of Wang–Mendel is compared to a new architecture of neural fuzzy production network based on the model of Mamdani–Zadeh. Learning results of these models are given in the interpretation of logical operations provided by Godel, Goguen and Lukasiewicz algebras. New Wang–Mendel's network can use minimum or sum-based formula as $T$-norm operation in accordance with an appropriate algebra rather than the standard multiplication only. Mamdani–Zadeh's network is designed as a cascade of $T$-norm, implication and S-norm operations defined by selected algebra. Moreover defuzzification layer is not presented in Mamdani–Zadeh's network. Both networks have several outputs in accordance with the number of subject area classes what differs them from the basic realizations. Compliance degrees of an input vector to defined classes are formed at the network outputs. To compare the models the standard Fisher's irises and Italian wines classification problems were used. This article presents the results calculated by training the networks by backpropagation algorithm. Classification error analysis shows that the use of these algebras as interpreting fuzzy logic operations proposed in this paper can reduce the classification error for both multi-output network of Wang-Mendel and a new network of Mamdani–Zadeh. The best learning results are shown by Godel algebra, but Lukasiewicz algebra demonstrates better generalizing properties while testing, what leads to a less number of classification errors.

Détail

Keywords: classification problem, neural fuzzy production based network, network of Wang-Mendel, model of Mamdani-Zadeh.

Bibliographie

[1] L. X. Wang, J. M. Mendel, “Generating fuzzy rules by learning from examples”, IEEE Trans. Syst., Man, Cybern., 22:6 (1992), 1414–1427 | DOI | MR

[2] Li-Xin Wang, “The WM method completed: a flexible fuzzy system approach to data mining”, IEEE Trans. Fuzzy Systems, 11:6 (2003), 768–782 | DOI

[3] L. A. Zadeh, “Fuzzy logic, neural networks, and soft computing”, Communications of the ACM, 37:3 (1994), 77–84 | DOI | MR

[4] E. H. Mamdani, “Application of Fuzzy Logic to Approximate Reasoning Using Linguistic Synthesis”, IEEE Trans. Computers, C-26:12, 1182–1191 | DOI

[5] S. Osovskiy, Neyronnyye seti dlya obrabotki informatsii [Neural networks for information processing], Finansy i statistika, Moscow, 2002, 344 pp. (In Russian)

[6] O. P. Soldatova, “Multifunctional simulator of neural networks”, Programmnyye produkty i sistemy, 2012, no. 3, 27–31 (In Russian)

[7] D. Rutkovskaya, M. Pilin'skiy, L. Rutkovskiy, Neyronnyye seti, geneticheskiye algoritmy i nechotkiye sistemy [Neural networks, genetic algorithms and fuzzy systems], Goryachaya liniya–Telekom, M., 2007, 452 pp. (In Russian)

[8] V. Novák, I. Perfilieva, J. Močkoř, Mathematical Principles of Fuzzy Logic, The Springer International Series in Engineering and Computer Science, 517, Springer, 1999, xiii+320 pp. ; V. Novak, I. Perfileva, I. Mochkorzh, Matematicheskie printsipy nechetkoi logiki, M., Fizmatlit, 2006, 352 pp. | DOI | MR

[9] V. V. Borisov, V. V. Kruglov, A. S. Fedulov, Nechetkiye modeli i seti [Fuzzy models and networks], Goryachaya liniya–Telekom, Moscow, 2007, 284 pp.

[10] A. S. Katasev, “Mathematical and software for fuzzy-productions knowledge bases generation of the expert diagnostic systems”, Fundamental'nyye issledovaniya, 2013, no. 10-9, 1922–1927 (In Russian)

[11] V. V. Bukhtoyarov, “Evolutionary three-stage approach for designing of neural networks ensembles for classification problems”, Programmnyye produkty i sistemy, 2012, no. 4, 101–106 (In Russian)