Bayesian estimation of a spectrum of a nonstationary autoregressive process

  • Maciej Niedźwiecki
Session 1 Non Stationary Processes
Part of the Lecture Notes in Control and Information Sciences book series (LNCIS, volume 62)


The new parametric spectrum estimator for the purpose of nonstationary autoregressive process analysis is presented. The proposed estimator is obtained by minimization of the Bayesian risk function corresponding to the normalized mean square spectral error measure. The obtained results concern the two most frequently used models of process parameters' variation : the Kalman filter model and the fadding memory (exponential forgetting) one. The efficient computational algorithms are indicated and the results of computer simulation are presented.


Spectrum Estimator Nonstationary Process Autoregressive Coefficient Fadding Memory Kalman Filter 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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Y.Grenier, "Rational non-stationary spectra and their estimation", 1-st ASSP Workshop on Spectral Estimation,Hamilton,Ontario,Canada, Aug.17–18,1981.Google Scholar
  2. [2]
    P. Eykhoff, "System Identification: Parameter and State Estimation" London: Wiley, 1974.Google Scholar
  3. [3]
    A.P. Sage and J.L. Melsa, "Estimation Theory with Applications to Communications and Control", New York: McGraw-Hill, 1971.Google Scholar
  4. [4]
    T. Bohlin, "Four cases of identification of changing systems", in: System Identification: Advances and Case Studies, R.K. Mehra and D.G. Lainiotis, eds., pp.441–518, Academic Press, New York, 1976.Google Scholar
  5. [5]
    A.Isaksson, "On the time variable properties of EEG signals examined by means of a Kalman filter method", Royal Institute of Technology, Stockholm, Technical Report No.95, April 1975.Google Scholar
  6. [6]
    V.Peterka, "Subjective probability approach to real-time identification", 4th IFAC Symposium on Identification and System Parameter Estimation,Tbilisi,Sept.1976,Part 3,pp.83–96.Google Scholar
  7. [7]
    M.Niedźwiecki, "On the localized estimators and generalized Akaike's criteria", to appear in IEEE Trans.Autom.Contr. see also 20th IEEE Conference on Decision and Control, San Diego, Dec.16–18,1981,pp.56–61.Google Scholar
  8. [8]
    J.D. Markel and A.H. Gray, Jr., "Linear Prediction of Speech", New York: Springer-Verlag, 1976.Google Scholar
  9. [9]
    A.Isaksson, "Examples of EEG signals with time-varying spectra analysed by means of a Kalman filter method", Royal Institute of Technology, Stockholm, Technical Report No.96,April 1975.Google Scholar
  10. [10]
    V. Strejc, "Least squares parameter estimation", Automatica, vol.16, pp.535–550,1980.Google Scholar
  11. [11]
    V. Peterka, "Bayesian system identification", Automatica, vol.17, pp.41–53,1981.Google Scholar
  12. [12]
    J.P. Burg, "The relationship between maximum entropy spectra and maximum likelihood spectra", Geophysics, vol.37,pp.375–376, April 1972.Google Scholar

Copyright information

© Springer-Verlag 1984

Authors and Affiliations

  • Maciej Niedźwiecki
    • 1
  1. 1.Institute of Computer ScienceTechnical University of GdańskGdańskPoland

Personalised recommendations