A FORECASTING NEURO-FUZZY NETWORK BASED ON A MULTIDIMENSIONAL NEO-FUZZY NEURON AND ITS LEARNING PROCEDURE

Authors

  • O. K. Tyshchenko Kharkiv National University of Radio Electronics, Ukraine, Ukraine
  • I. P. Pliss Kharkiv National University of Radio Electronics, Ukraine, Ukraine
  • K. O. Shkuro Kharkiv National University of Radio Electronics, Ukraine, Ukraine

DOI:

https://doi.org/10.15588/1607-3274-2014-2-17

Keywords:

computational intelligence, multidimensional neo-fuzzy neuron, learning procedure, time series prediction, membership function.

Abstract

A forecasting neuro-fuzzy network designated for solving extrapolation tasks of multidimensional nonlinear non-stationary stochastic and chaotic time series under conditions of a short learning sample is proposed in the paper. The network is built with the help of a multidimensional neo-fuzzy neuron with an input layer which is organized in a special manner and a spline membership function. The proposed system provides high approximation quality in terms of a mean square error and high convergence speed on account of using the second-order learning procedure. A software that implements the proposed neuro-fuzzy network has been developed. A number of experiments has been held in order to research the system’s properties. Experimental results prove the fact that the developed architecture could be used in Data Mining tasks and the fact that the proposed neuro-fuzzy network has higher accuracy compared to traditional forecasting neuro-fuzzy systems.

References

Cichocki A. Neural Networks for Optimization and Signal Processing / A. Cichocki, R. Unbehauen. – Stuttgart : Teubner, 1993. – 526 p. 2. Haykin S. Neural Networks. A Comprehensive Foundation / S. Haykin. – Upper Saddle River: Prentice Hall, 1999. – 842 p. 3. Schalkoff R. J. Artificial Neural Networks / R. J. Schalkoff. – N. Y. : The McGraw-Hill Comp., 1997. – 528 p. 4. Jang J.-S. Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intalligence / J.-S. Jang, C.-T. Sun, E. Mizutani. – Upper Saddle River : Prentice Hall, 1997. – 640 p. 5. Osowski S. Sieci neuronowe do przetwarzania informacij / S. Osowski. – Warszawa : Oficijna Wydawnicza Politechniki Warszawskiej, 2006. – 422 p. 6. Du K.-L. Neural Networks and Statistical Learning / K.-L. Du, M. N. S. Swamy. – London : Springer-Verlag, 2014. – 815 p. 7. Rutkowski L. Computational Intelligence. Methods and Techniques / L. Rutkowski. – Berlin : Springer-Verlag, 2008. – 514 p. 8. Mumford C. L. Computational Intelligence / C. L. Mumford, L. C. Jain. – Berlin : Springer-Verlag, 2009. – 725 p. 9. Kruse R. Computational Intelligence. A Methodological Introduction / [R. Kruse, C. Borgelt, F. Klawonn et al]. – Berlin : Springer-Verlag, 2013. – 488 p.

Published

2014-11-11

How to Cite

Tyshchenko, O. K., Pliss, I. P., & Shkuro, K. O. (2014). A FORECASTING NEURO-FUZZY NETWORK BASED ON A MULTIDIMENSIONAL NEO-FUZZY NEURON AND ITS LEARNING PROCEDURE. Radio Electronics, Computer Science, Control, (2). https://doi.org/10.15588/1607-3274-2014-2-17

Issue

Section

Neuroinformatics and intelligent systems