Adaptive MV ARMA Identification Under the Presence of Noise

  • Stylianos Sp. Pappas
  • Vassilios C. Moussas
  • Sokratis K. Katsikas
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 27)


An adaptive method for simultaneous order estimation and parameter identification of multivariate (MV) ARMA models under the presence of noise is addressed. The proposed method is based on the well known multi-model partitioning (MMP) theory. Computer simulations indicate that the method is 100% successful in selecting the correct model order in very few steps. The results are compared with two other established order selection criteria, namely, Akaike’s information criterion (AIC) and Schwarz’s Bayesian information criterion (BIC).


Root Mean Square Error Posterior Probability Kalman Filter Bayesian Information Criterion Model Order 
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 paper is dedicated to the memory of Prof. Dimitrios G. Lainiotis, the founder of the multi-model partitioning theory, who passed away suddenly in 2006.


  1. 1.
    Lu S, Ju KH, Chon KH (2001) A new algorithm for linear and nonlinear ARMA model parameter estimation using affine geometry [and application to blood flow/pressure data]. IEEE T Biomed Eng 48(10):1116–1124CrossRefGoogle Scholar
  2. 2.
    Derk J, Weber S, Weber C (2007) Extended ARMA models for estimating price developments on day-ahead electricity markets. Elec Power Syst Res 77(5–6):583–593Google Scholar
  3. 3.
    Chen CP, Bilmes JA (2007) MVA processing of speech features. IEEE T Audio Speech 15(1):257–270CrossRefGoogle Scholar
  4. 4.
    Kourosh M, Eslami HR, Kahawita R (2006) Parameter estimation of an ARMA model for river flow forecasting using goal programming. J Hydrol 331(1–2):293–299Google Scholar
  5. 5.
    Pappas Sp S, Leros AK, Katsikas SK (2006) Joint order and parameter estimation of multivariate autoregressive models using multi-model partitioning theory. Dig Signal Process 16(6):782–795CrossRefGoogle Scholar
  6. 6.
    Lainiotis DG (1976) Partitioning: a unifying framework for adaptive systems I: Estimation. Proc IEEE 64:1126–1143CrossRefMathSciNetGoogle Scholar
  7. 7.
    Lainiotis DG (1976) Partitioning: a unifying framework for adaptive systems I: Control. Proc IEEE 64:1182–1198CrossRefMathSciNetGoogle Scholar
  8. 8.
    Akaike H (1969) Fitting autoregressive models for prediction. Ann Inst Stat Math 21:243–247CrossRefMATHMathSciNetGoogle Scholar
  9. 9.
    Rissanen J (1978) Modelling by shortest data description. Automatica 14:465–471CrossRefMATHGoogle Scholar
  10. 10.
    Rissanen J (1986) A predictive least squares principle. IMA J Math Contr Inform 3:211–222CrossRefMATHGoogle Scholar
  11. 11.
    Schwarz G (1978) Estimation of the dimension of the model. Ann Statist 6:461–464CrossRefMATHMathSciNetGoogle Scholar
  12. 12.
    Wax M (1988) Order selection for AR models by predictive least squares. IEEE T Acoust Speech Signal Process 36:581–588CrossRefMATHGoogle Scholar
  13. 13.
    Lutkepohl H (1985) Comparison of criteria for estimating the order of a vector AR process J Time Ser Anal 6:35–52CrossRefMathSciNetGoogle Scholar
  14. 14.
    Sage AP, Husa GW (1969) Adaptive filtering with unknown prior statistics. In: Proceedings of the Joint Automatic Control Conference, Boulder, Colorado, pp 760–769Google Scholar
  15. 15.
    Watanabe K (1992) Adaptive estimation and control: partitioning approach.:Prentice Hall, Englewood Cliffs, NJGoogle Scholar
  16. 16.
    Katsikas SK, Leros AK, Lainiotis DG (1994) Passive tracking of a maneuvering target: an adaptive approach. IEEE T Signal Process 42(7):1820–1825CrossRefGoogle Scholar
  17. 17.
    Katsikas SK, Likothanassis SD, Beligiannis GN, Berkeris KG, Fotakis DA (2001) Genetically determined variable structure multiple model estimation. IEEE T Signal Process 49(10):2253–2261CrossRefGoogle Scholar
  18. 18.
    Lainiotis DG, Papaparaskeva PA (1998) Partitioned adaptive approach to nonlinear channel equalization. IEEE T Commun 46(10):1325–1336CrossRefGoogle Scholar
  19. 19.
    Moussas VC, Likothanassis SD, Katsikas SK, Leros AK (2005) Adaptive online multiple source detection. In: IEEE International Conference on Acoustics Speech and Signal Processing Proceedings (ICASSP ’05,), 4:1029–1032CrossRefGoogle Scholar
  20. 20.
    Lainiotis DG, Katsikas SK, Likothanassis SD (1988) Adaptive deconvolution of seismic signals: performance, computational analysis parallelism. IEEE T Acoust Speech Signal Process 36(11):1715–1734CrossRefMATHGoogle Scholar
  21. 21.
    Sengbush RL, Lainiotis DG (1969) Simplified parameter quantization procedure for adaptive estimation. IEEE T Automat Contr AC-14:424–425CrossRefGoogle Scholar
  22. 22.
    Anderson BDO, Brinsmead TS, Bruyne FDe, Hespanha J, Liberzon D, Morse AS (2000) Multiple model adaptive control part 1: finite controller coverings. Int J Robust Nonlinear Contr 10:909–929CrossRefMATHGoogle Scholar
  23. 23.
    Hawks RM, Moore JB (1976) Performance of Bayesian parameter estimators for linear signal models. IEEE T Automat Contr AC–21:523–527CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  • Stylianos Sp. Pappas
    • 1
  • Vassilios C. Moussas
    • 2
  • Sokratis K. Katsikas
    • 3
  1. 1.Department of Information and Communication Systems EngineeringUniversity of the AegeanGreece
  2. 2.School of Technological Applications (S.T.E.F.), Technological Educational Institution (T.E.I.) of AthensGreece
  3. 3.Department of Technology Education and Digital SystemsUniversity of PiraeusGreece

Personalised recommendations