Complex Neural Models of Dynamic Complex Systems: Study of the Global Quality Criterion and Results

  • G. Drałus
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 99)


In this paper dynamic global models of input-output complex systems are discussed. Dynamic complex system which consists of two nonlinear discrete time sub-systems is considered. Multilayer neural networks in a dynamic structure are used as a global model. The global model is composed of two sub-models according to the complex system. A quality criterion of the global model contains coefficients which define the participation of sub-models in the global model. The main contribution of this work is the influence study on the global model quality of these coefficients. That influence is examined for different back propagation learning algorithms for complex neural networks.


Learning Algorithm Quality Index Global Model Work Mode Dynamic Complex System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [Dahleh and Venkatesh 1997]
    Dahleh, M.A., Venkatesh, S.: System Identification of complex systems; Problem formulation and results. In: Proc. of 36th Conf. on Decision & Contol, San Diego, CA, pp. 2441–2446 (1997)Google Scholar
  2. [Drałus 2004]
    Drałus, G.: Modeling of dynamic nonlinear complex systems using neural networks. In: Proc. of the 15th International Conference on Systems Science, Wroclaw, Poland, vol. III, pp. 87–96 (2004)Google Scholar
  3. [Drałus and Świątek 2009]
    Drałus, G., Świątek, J.: Static and dynamic complex models: comparison and application to chemical systems. Kybernetes: The Int. J. of Systems & Cybernetics 38(7/8) (2009)Google Scholar
  4. [Drałus 2010]
    Drałus, G.: Study on quality of complex models of dynamic complex systems. In: 3rd Conference on Human System Interactions, Digital Object Identifier, pp. 169–174 (2010), doi:10.1109/HSI.2010.5514570Google Scholar
  5. [Drapała and Światek 2006]
    Drapała, J., Światek, J.: Modeling of dynamic complex systems by neural networks. In: Proc. of 18th Int. Conf. on Systems Engineering, Coventry University, UK, pp. 109–112 (2006)Google Scholar
  6. [Gupta et al. 2003]
    Gupta, M.M., Jin, L., Homma, N.: Static and dynamic neural networks – from fundamentals to advanced theory. John Wiley & Sons, Inc., Chichester (2003)CrossRefGoogle Scholar
  7. [Hornik 1989]
    Hornik, K.: Multilayer feedforward networks are universal approximators. Neural Networks 2, 359–366 (1989)CrossRefGoogle Scholar
  8. [Hunt and all, 1992]
    Hunt, K.J., Sbarbaro, D., Zbikowski, R., Gawthrop, P.J.: Neural networks for control systems – A survey. Automatica 28(8), 1083–1112 (1992)MathSciNetCrossRefGoogle Scholar
  9. [Narendra and Parthasarathy 1990]
    Narendra, K.S., Parthasarathy, K.: Identification and control of dynamic systems using neural network. IEEE Trans. on Neural Networks 1(1), 4–27 (1990)CrossRefGoogle Scholar
  10. [Jacobs 1988]
    Jacobs, R.A.: Increased rates of convergence through learning rate adaptation. Neural Networks 1, 295–307 (1988)CrossRefGoogle Scholar
  11. [Osowski 2007]
    Osowski, S.: Modeling and simulation of dynamic systems and processes. Warsaw University of Technology Publishing House (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • G. Drałus
    • 1
  1. 1.Department of Electrical Engineering FundamentalsRzeszow University of TechnologyRzeszowPoland

Personalised recommendations