Self-Adaptive Evolution Strategies for the Adaptation of Non-Linear Predictors in Time Series Analysis

  • André Neubauer
Chapter
Part of the Applied and Numerical Harmonic Analysis book series (ANHA)

Abstract

The application of evolutionary computation techniques to the prediction of nonlinear and non-stationary stochastic signals is presented — a task that arises, e.g., in time series analysis. Especially, the online adaptation of bilinear predictors with the help of a multi-membered (μ, λ) — evolution strategy with self-adaptation of strategy parameters is treated. Special emphasis is given to the tracking capabilities of this specific evolutionary algorithm in non-stationary environments. The novel modifications of the standard (μ, λ) — evolution strategy are detailed that are necessary to obtain a computationally efficient algorithm. Using the evolutionary adapted bilinear predictor as part of a bilinear prediction error filter, the proposed methodology is applied to estimating bilinear stochastic signal models. Experimental results are given that demonstrate the robustness and efficiency of the (μ, λ) — evolution strategy in this digital signal processing application.

Keywords

Genetic Algorithm Time Series Analysis Strategy Parameter Adaptive Filter Error Criterion 
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.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    T. Bäck. Evolutionary Algorithms in Theory and Practice. Oxford University Press, New York, 1996.MATHGoogle Scholar
  2. [2]
    D. M. Etter, M. J. Hicks, and K. H. Cho. Recursive Adaptive Filter Design Using an Adaptive Genetic Algorithm. In: Proceedings of the 1982 IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP’82. 2:635–638, 1982.Google Scholar
  3. [3]
    D. B. Fogel. System Identification Through Simulated Evolution: A Machine Learning Approach to Modeling. Ginn Press, Needham Heights, 1991.Google Scholar
  4. [4]
    D. B. Fogel. Evolutionary Computation: Toward a New Philosophy of Machine Intelligence. IEEE Press, New York, 1995.Google Scholar
  5. [5]
    L. J. Fogel, A. J. Owens, and M. J. Walsh. Artificial Intelligence Through Simulated Evolution. John Wiley & Sons, New York, 1966.MATHGoogle Scholar
  6. [6]
    S. Haykin. Adaptive Filter Theory. Prentice-Hall, Englewood Cliffs, N.J., 1986.Google Scholar
  7. [7]
    J. H. Holland. Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence. First MIT Press Edition, Cambridge, 1992.Google Scholar
  8. [8]
    J. R. Koza. Genetic Programming: On the Programming of Computers by Means of Natural Selection. The MIT Press, Cambridge, 1992.MATHGoogle Scholar
  9. [9]
    J. Lee and V. J. Mathews. Adaptive Bilinear Predictors. In: Proceedings of the 1994 IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP’94. Adelaide, 3:489–492, 1994.Google Scholar
  10. [10]
    V. J. Mathews. Adaptive Polynomial Filters. In: IEEE Signal Processing Magazine. 8(3):10–26, 1991.CrossRefGoogle Scholar
  11. [11]
    J. R. McDonnell and D. Waagen. Evolving Recurrent Perceptrons for Time-Series Modeling. In: IEEE Transactions on Neural Networks: Special Issue on Evolutionary Computation. 5(1):24–38, 1994.CrossRefGoogle Scholar
  12. [12]
    A. Neubauer. Linear Signal Estimation Using Genetic Algorithms. In: Systems Analysis Modelling Simulation. Gordon and Breach Science Publishers, Amsterdam, 18/19: 349-352, 1995.Google Scholar
  13. [13]
    A. Neubauer. Real-Coded Genetic Algorithms for Bilinear Signal Estimation. In: D. Schipanski (Hrsg.): Tagungsband des 40. Internationalen Wissenschaftlichen Kolloquiums. Ilmenau, Band 1, 347–352, 1995.Google Scholar
  14. [14]
    A. Neubauer. Non-Linear Adaptive Filters Based on Genetic Algorithms with Applications to Digital Signal Processing. In: Proceedings of the 1995 IEEE International Conference on Evolutionary Computation ICEC’95. Perth, 2:527–532, 1995.CrossRefGoogle Scholar
  15. [15]
    A. Neubauer. Genetic Algorithms for Non-Linear Adaptive Filters in Digital Signal Processing. In: K.M. George, J.H. Carroll, D. Oppenheim., and J. High-tower. (Eds.) Proceedings of the 1996 ACM Symposium on Applied Computing SAC’96. Philadelphia, 519-522, 1996.Google Scholar
  16. [16]
    A. Neubauer. A Comparative Study of Evolutionary Algorithms for On-Line Parameter Tracking. In: H.-M. Voigt, W. Ebeling, I. Rechenberg, and H.-P. Schwefel. (Eds.) Parallel Problem Solving from Nature PPSN IV. Springer-Verlag, Berlin, 624–633, 1996.CrossRefGoogle Scholar
  17. [17]
    A. Neubauer. Prediction of Nonlinear and Nonstationary Time-Series Using Self-Adaptive Evolution Strategies with Individual Memory. In: Bäck, Th. (Ed.): Proceedings of the Seventh International Conference on Genetic Algorithms ICGA’97. Morgan Kaufmann Publishers, San Francisco,727–734, 1997.Google Scholar
  18. [18]
    A. Neubauer. On-Line System Identification Using The Modified Genetic Algorithm. In: Proceedings of the Fifth Congress on Intelligent Techniques and Soft Computing EUFIT’91. Aachen, 2:764–768, 1997.Google Scholar
  19. [19]
    A. Neubauer. Genetic Algorithms in Automatic Fire Detection Technology. In: IEE Proceedings of the 2nd International Conference on Genetic Algorithms in Engineering Systems: Innovations and Applications GALESIA’97. Glasgow, 180-185, 1997.Google Scholar
  20. [20]
    A. Neubauer. Adaptive Filter auf der Basis genetischer Algorithmen. VDI-Verlag, Düsseldorf, 1997.Google Scholar
  21. [21]
    M. B. Priestley. Non-linear and Non-stationary Time Series Analysis. 1st Paperback Edition, Academic Press, London, 1991.MATHGoogle Scholar
  22. [22]
    I. Rechenberg. Evolutionsstrategie’94. Prommann-Holzboog, Stuttgart, 1994.Google Scholar
  23. [23]
    H.-P. Schwefel. Numerical Optimization of Computer Models. John Wiley & Sons, Chichester, 1981.MATHGoogle Scholar
  24. [24]
    H.-P. Schwefel. Evolution and Optimum Seeking. John Wiley & Sons, New York, 1995.Google Scholar
  25. [25]
    P. Strobach. Linear Prediction: A Mathematical Basis for Adaptive Systems. Springer-Verlag, Berlin, 1990.CrossRefMATHGoogle Scholar
  26. [26]
    T. Subba Rao and M. M. Gabr. An Introduction to Bispectral Analysis and Bilinear Time Series Models. Springer-Verlag, Berlin, 1984.MATHGoogle Scholar
  27. [27]
    H. Tong. Non-linear Time Series: A Dynamical System Approach. Oxford University Press, New York, 1990.MATHGoogle Scholar
  28. [28]
    M. S. White and S. J. Flockton. Genetic Algorithms for Digital Signal Processing. In: T. C. Fogarty. (Ed.): Evolutionary Computing. Springer-Verlag, Berlin, 291–303, 1994.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 1998

Authors and Affiliations

  • André Neubauer
    • 1
  1. 1.Siemens AGMicroelectronics Design CenterDüsseldorfGermany

Personalised recommendations