One Approach for Training of Recurrent Neural Network Model of IIR Digital Filter

  • S.A. Stefanova
Conference paper

Abstract

One approach for training of recurrent neural network model of 1-D IIR digital filter is proposed. The sensitivity coefficients method has been applied in the training process of the neural network. The set of time domain data is generated and used as a target function in the training procedure. The modeling results have been obtained for two different cases - for 4-th order bandpass IIR digital filter and for partial response IIR digital filter. The frequency domain behavior of the neural network model and the target IIR filter has been investigated. The analysis of the frequency responses shows good approximation results.

Keywords

Neural Network Model Digital Filter Recurrent Neural Network Magnitude Response Recurrent Neural Network Model 
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]
    Jin L., P. Nikiforuk, and M. Gupta, “Approximation of discrete-time state-space trajectories using dynamical recurrent neural networks”, IEEE Transactions on Automatic Control, Vol. 40, No 7, 1995.Google Scholar
  2. [2]
    H. Cruse , Neural Networks as Cybernetic Systems, Brains, Minds and Media, Bielefeld, Germany, October 2006.Google Scholar
  3. [3]
    M. Pedersen, “Optimization of recurrent neural networks for time domain series modeling”, Ph.D Thesis, Department of Mathematical Modeling, Technical University of Denmark, 1997.Google Scholar
  4. [4]
    J. Cao, Yahagi T., “Nonlinear adaptive digital filters using parallel neural networks”, Proceedings of IEEE International Conference on Neural Networks, Vol. 2, Nov-Dec 1995 pp. 850 – 853.CrossRefGoogle Scholar
  5. [5]
    D. Bhattacharya, and A. Antoniou, Real-time design of FIR filter by feedback neural network, IEEE Signal Processing Letters, Vol.3, No 4, May 1996, pp. 158 – 161.CrossRefGoogle Scholar
  6. [6]
    Zhe-Zhao Zeng; Ye Chen; Yao-Nan Wang, ”Optimal Design Study of High-Order FIR Digital Filters Based on Neural-Network Algorithm”, International Conference on Machine Learning and Cybernetics, 13-16 Aug. 2006, pp 3157 – 3161.Google Scholar
  7. [7]
    Zeng Zhe-zhao; Wen Hui, “Optimal design study of three-type FIR high-order digital filters based on sine basis functions neural-network algorithm”, IEEE International Symposium on Communications and Information Technology, Vol. 2, No 12-14 ,pp. 921- 924, October 2005.Google Scholar
  8. [8]
    X. H. Wang, Y. G. He, H. Li, Y. L. Peng, M.J. Li, “Design of 2-D digital filters using back propagation neural networks”, Proceedings of International Conference on Machine Learning and Cybernetic, 18-21 Aug. 2005, Vol. 8, pp 4684 – 4689.CrossRefGoogle Scholar
  9. [9]
    Wang D. and A. Zilouchian, Intelligent control systems using soft computing methodologies, Editors: Ali Zilouchian, Mo Jamshidi, Prentice Hall, March 2001, pp, 93-110.Google Scholar
  10. [10]
    Chow, T.W.S. Siu-Yeung Cho “An accelerated recurrent network training algorithm using IIR filter model and recursive least squares method” IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, Vol. 44, No 11, Nov, 1997, pp. 1082-1086.CrossRefGoogle Scholar
  11. [11]
    Bhattacharya, D.; Antoniou, A., “Design of IIR filters with arbitrary amplitude and phase responses by feedback neural networks”, IEEE International Symposium on Circuits and Systems, ISCAS ’96, Vol. 3, 12-15 May 1996, pp. 457 – 460.Google Scholar
  12. [12]
    Mladenov, V.M., Mastorakis, N.E., “Design of two-dimensional recursive filters by using neural networks”, IEEE Transactions on Neural Networks, Vol. 12, No 3, May 2001, pp. 585 – 590.CrossRefGoogle Scholar
  13. [13]
    W. T. Miller, R. S. Sutton and P. J. Werbos, Neural Networks for Control., Cambridge, MA:MIT Press, 1990.Google Scholar
  14. [14]
    R. Grino, G. Cembrano and C. Torras, “Nonlinear system identification using additive dynamic neural networks – two on-line approaches”, IEEE Trans. on Circuits and Systems I, vol. 47, no.2, 2000, pp. 150-165.CrossRefGoogle Scholar
  15. [15]
    Y. Fang, M. Yagoub, F. Wang and Qi-J. Zhang, “A new macromodeling approach for nonlinear microwave circuits based on recurrent neural networks”, IEEE Trans. on Microwave Theory and Techniques, Vol. 48, no. 2, Dec. 2000, pp. 2335-2344CrossRefGoogle Scholar
  16. [16]
    Stefanova S., “One Dimensional IIR digital filter modeling based on recurrent neural network”, International Joint Conferences on Computer, Information, and Systems Sciences, and Engineering (CISSE 08), University of Bridgeport, Bridgeport, U.S.A, December 5 - 13, 2008.Google Scholar
  17. [17]
    S. Pei, Ch. Hsu, P. Wang, “Design of a class of IIR eigenfilters with time and frequency domain constraint, IEEE Trans. on Circuits and Systems-II Analog and Digital Signal Processing, vol. 49, No 2, February 2002, pp 145 - 151.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2010

Authors and Affiliations

  • S.A. Stefanova
    • 1
  1. 1.Department of Electronic Engineering and TechnologiesTechnical University of SofiaSofiaBulgaria

Personalised recommendations