Abstract. 

The paper addresses the problem of computational complexity of fuzzy inference. An outline of common fuzzy inference methods is provided. Since these methods cannot be used in case of multiple fuzzy inputs due to exponential computational complexity, another inference method is introduced. This method is based on fuzzy truth value, and it is free of the described drawback. The operation of the method is described further. The article provides a formal definition of the method for a single fuzzy rule as well as for multiple rules. Then, the issue of machine learning of such systems is concerned, including the parameters that can undergo adjustment and objective function. In the article, training by means of evolution strategy (μ, λ) is assumed. Finally, the described approach is being assessed in terms of approximation quality of a specific known function.

Keywords: 

Fuzzy Systems, Neuro-fuzzy Systems, Evolution Strategies.

 

PP. 3-11.

 

DOI 10.14357/20718632200101

 

References

1. Zadeh, L.A. 1973. Outline of a New Approach to the Analysis of Complex Systems and Decision Processes. IEEE Trans. of Systems, Man and Cybernetics. 3(1):28–42.

2. Mamdani, E.H. 1974. Application of Fuzzy Algorithm for Control a Simple Dynamic Plant. Proc. IEEE. 121(12):1585–1588.

3. Larsen, P.M. 1980. Industrial Applications of Fuzzy Logic Control. Intern. J. Man-Machine Studies. 12(1):3–10.

4. Takagi, T. and M. Sugeno. 1985. Fuzzy identification of systems and its applications to modeling and control. IEEE Trans. of System. Man. and Cybernetics. 15(1):116–132.

5. Tsukamoto, Y. 1979. An Approach to Fuzzy Reasoning Method. Advances in Fuzzy Sets Theory and Applications. North-Holland, Amsterdam. pp. 137–149.

6. Leonenkov, A.V. 2003. Nechyotkoye modelirovaniye v srede MATLAB i fuzzyTECH [Fuzzy modeling in MATLAB and FuzzyTech environment]. Saint Petersburg: BHV – Petersburg. 736 p.

7. Rothstein, A.P. and S.D. Shtovba. 2006. Identifikatsiya nelineynoy zavisimosti nechyotkoy obuchayuschey vyborkoy [Identification of Nonlinear Dependence by Fuzzy Training Set]. Cybernetics and System Analysis. 2:116–132.

8. Borisov, V.V., V.V. Kruglov and A.S. Fedulov. 2012. Nechyotkiye modeli i seti [Fuzzy models and networks]. Moscow: Hot Line – Telecom. 285 p.

9. Rutkowsky, L. 2010. Metody i tekhnologii iskusstvennogo intellekta [Methods and techniques of computational intelligence]. Moscow: Hot Line – Telecom. 520 p.

10. Rutkowska, D., M. Pilinsky and L. Rutkowsky. 2006. Neyronniye seti, geneticheskiye algoritmy i nechyotkiye sistemy [Neural networks, genetic algorithms and fuzzy systems]. Moscow: Hot Line – Telecom. 452 p.

11. Sinuk, V.G., V.M. Polyakov and D.A. Kutsenko. 2016. New Fuzzy Truth Value Based Inference Methods for Non-singleton MISO Rule-Based Systems. In: Proc. of the First Intern. Scientific Conf. «Intelligent Information Technologies for Industry» (IITI’16). Advances in Intelligent Systems and Computing. 450:395–405.

12. Mikhelev, V.V. and V.G. Sinuk. 2018. Metody vyvoda dlya system logicheskogo tipa na osnove nechyotkoy stepeni istinnosti [Inference Methods for Logical-Type Systems Based on Fuzzy Truth Degree]. Bulletin of the Russian Academy of Sciences: Control Theory and Systems. 57(3):108–115.

13. Borisov, A.N., A.V. Alekseev, O.A. Krunberg et al. 1982. Modeli prinyatiya resheniy na osnove lingvisticheskoy peremennoy [Decision making models based on linguistic variable]. Riga: Zinatne. 256 p.

14. Zadeh, L.A. 1978. PRUF — A Meaning Representation Language for Natural Language. Intern. J. Man-Machine Studies. 10(4):395–460.

15. Dobuis, D. and H. Prade. 1990. Teoriya vozmozhnostey. Prilozheniye k predstavleniyu znaniy v informatike [Possibility theory. Applications to the representation of knowledge in Informatics]. Moscow: Radio and Communication. 287 p.

16. Kutsenko, D.A. and V.G. Sinuk. 2015. Metody vyvoda dlya system so mnogimi nechyotkimi vhodami [Inference method for systems with multiple fuzzy inputs]. Bulletin of the Russian Academy of Sciences: Control Theory and Systems. 54(3):375–383.