A Fuzzy MLP Approach for Identification of Nonlinear Systems

Cover Page

Cite item


In case of decision making problems, identification of non-linear systems is an important issue. Identification of non-linear systems using a multilayer perceptron (MLP) trained with back propagation becomes much complex with an increase in number of input data, number of layers, number of nodes, and number of iterations in computation. In this paper, an attempt has been made to use fuzzy MLP and its learning algorithm for identification of non-linear system. The fuzzy MLP and its training algorithm which allows to accelerate a process of training, which exceeds in comparing with classical MLP is proposed. Results show a sharp reduction in search for optimal parameters of a neuro fuzzy model as compared to the classical MLP. A training performance comparison has been carried out between MLP and the proposed fuzzy-MLP model. The time and space complexities of the algorithms have been analyzed. It is observed, that number of epochs has sharply reduced and performance increased compared with classical MLP.

About the authors

A R Marakhimov

National University of Uzbekistan named after M. Ulugbek

Email: avaz.marakhimov@yandex.ru
Tashkent, Uzbekistan

K K Khudaybergenov

National University of Uzbekistan named after M. Ulugbek

Email: kabul85@mail.ru
Tashkent, Uzbekistan


  1. Борисов В. В., Круглов В. В., Федулов А. С. Нечеткие модели и сети. 2-е изд. - М.: «Горячая линия - Телеком», 2012.
  2. Митюшкин Ю. И., Мокин Б. И., Ротштейн А. П. Soft Computing: идентификация закономерностей нечеткими базами знаний. - Вiнниця: Унiверсум, 2002.
  3. Пегат А. Нечеткое моделирование и управление. - М.: БИНОМ. Лаборатория знаний, 2013.
  4. Штовба С. Д. Проектирование нечетких систем средствами MATLAB. - М.: «Горячая линия - Телеком», 2007.
  5. Galushkin A. I. Neural networks theory. - Berlin-Heidelberg: Springer-Verlag, 2007.
  6. Haykin S. Neural networks. A comprehensive foundation. 2nd ed. - New York: IEEE, 1999.
  7. Jose K. M., Fabio M. A. Nonlinear system identification based on modified ANFIS// Proc. 2015 12th Int. Conf. on Informatics in Control, Automation and Robotics (ICINCO), Colmar, France, 21-23 July 2015. - Colmar, 2015. - С. 588-595.
  8. Nikov A., Georgiev T. A fuzzy neural network and its matlab simulation// Proc. ITI99 21st Int. Conf. on Information Technology Interfaces, Pula, Croatia, June 15-18. - Pula, 1999. - С. 413-418.
  9. Qing-Song M. Approximation ability of regular fuzzy neural networks to fuzzy-valued functions in MS convergence structure// Proc. 32nd Chinese Control Conf., Xian, China, 26-28 July 2013. - Xian, 2013. - INSPEC Acc. Num. 13862419.
  10. Rakesh B. P., Satish K. Sh. Identification of nonlinear system using computational paradigms// Proc. Int. Conf. on Automatic Control and Artificial Intelligence, Xiamen, China, 3-5 March 2012. - Xiamen, 2012. - С. 1156-1159.
  11. Rotshtein A. P. Design and tuning of fuzzy if-then rules for medical diagnosis// В сб.: «Fuzzy and neural- fuzzy systems in medical and biomedical engineering». - Boca-Raton: CRC Press, 1998. - С. 243-289.
  12. Rotshtein A. P., Mityushkin Y. I. Extraction of fuzzy rules from experimental data using genetic algorithms// Cybernet. Systems Anal. - 2001. - № 3. - С. 45-53.
  13. Rotshtein A. P., Shtovba S. D. Identification of non-linear dependencies of fuzzy knowledge bases with fuzzy learning inputs// Cybernet. Systems Anal. - 2006. - № 2. - С. 17-24.
  14. Rumelhart D. E., Hinton G. E., Williams R. J. Learning internal representations by back-propagating errors// Nature. - 1986. - 323. - С. 533-536.
  15. Zimmermann H. J. Fuzzy set theory and its applications. - Dordrecht-Boston: Kluwer, 1991.
  16. Zongyuan Z., Shuxiang X., Byeong H. K., Mir M., Yunling L., Rainer W. Investigation and improvement of multi-layer perceptron neural networks for credit scoring// Expert Syst. Appl. - 2015. - 42, № 7. - С. 3508-3516.

This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies