Advertisement

Certain comments on data preparation for neural networks based modelling

  • Bartlomiej Beliczynski
Conference paper

Abstract

The process of data preparation for neural networks based modelling is examined. We are discussing sampling, preprocessing and decimation, finally urguing for orthonormal input preprocessing.

Keywords

Neural Network Data Preparation Linear Dynamical System Dynamic Transformation Neural Network Form 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    AH Chung Tsoi and A Back. Static and dynamic preprocessing methods in neural networks. Engng. Applic. Artif. Intell., 8(6):633–642, 1995.CrossRefGoogle Scholar
  2. [2]
    A. Pinkus M. Leshno, V. Lin and S. Schocken. Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Networks, 13:350–373, 1993.Google Scholar
  3. [3]
    L M Grzesiak, B Beliczynski, and B Ufnalski. Input preprocessing in tapped delay neural architecture for induction motor speed estimation. In Proc. EPE Conf. European Power Electronics Conference, Toulouse 2003., EPE, 2003.Google Scholar
  4. [4]
    P S C Heuberger and P M J Van Den Hof. A genelized orthonormal basis for linear dynamical systems. IEEE Trans, on Autom. Contr., 40:451–464, 1995.CrossRefMATHGoogle Scholar
  5. [5]
    B Nines and F Gustafsson. A unifying construction of orthonormal bases for system identification. IEEE Trans. Automat. Contr., 42:515–521, 1997.CrossRefGoogle Scholar
  6. [6]
    B Beliczynski and L Grzesiak. Induction motor speed estimation: Limitations of certain neural schemes based on time instances of periodic signals. In Proc. IECON’01, pages 653–657. IEEE Service Center, 2001.Google Scholar
  7. [7]
    B Beliczynski and L Grzesiak. Induction motor speed estimation: Neural versus phenomenological model approach. Neurocomputing, 43:17–36, 2002.CrossRefMATHGoogle Scholar
  8. [8]
    B Beliczynski. On input discretisation processes for tapped delay neural architecture. In Proc. ICANNGA ’03, pages 28–32. Springer, 2003.Google Scholar
  9. [9]
    B Beliczynski and K Kubowicz. Appoximately static relationship between model variables. Przeglad Elektrotechniczny, 53(4):385–389, 2004.Google Scholar

Copyright information

© Springer-Verlag/Wien 2005

Authors and Affiliations

  • Bartlomiej Beliczynski
    • 1
  1. 1.Institute of Control and Industrial ElectronicsWarsaw University of TechnologyWarsaw

Personalised recommendations