Abstract
In this paper, a robust identification method of the system model is proposed. The robustizing process is in the form of a Robbins-Monro stochastic approximation (RMSA) algorithm and is based on the m-interval polynomial approximation (MIPA) method. The resulting algorithm, which estimates the coefficients of the system model, represents a recursive robustized version of the well-known maximum entropy method (MEM) for spectral estimation introduced by Burg, or of the popular Widrow least-mean-square (LMS) adaptive filter adopted widely in engineering. Furthermore, the MIPA robustizing algorithm leads naturally to a robustized Akaike's information criterion (AIC) to determine the order of the system model. The simplicity of implementation and flexibility make applications of the MIPA identification algorithms attractive in practice. The robustness of performance is confirmed by Monte Carlo simulations.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
G.E.P. Box and G.M. Jenkins, "Time Series Analysis, Forcasting and Control," Holden-Day, California, 1976.
P.J. Huber, "Robust Regression: Asymptotics, Conjectures and Monte Carlo," Ann. of Statist., Vol. 1, pp. 799–821, 1973.
P.J. Huber, "Robust Estimation of a Location Parameter," Ann. Math. Statist, Vol. 35, pp. 73–101, 1964.
R.D. Martin and C.J. Masteliez, "Robust Estimation via Stochastic Approximation," IEEE Trans. Inform. Theory, Vol. IT-21, pp. 263–271, 1975.
B.T. Poljak and Ya. Z. Tsypkin, "Robust Identification," Automatica, Vol. 16, pp. 53–63, 1980.
L.A. Jackel, "Estimating Regression Coefficients by Minimizing the Dispersion of the Residuals," Ann. Math. Statist. Vol. 43, pp. 1449–1458, 1972.
J. Jureckova, "Nonparametric Estimates of Regression Coefficients," Ann. Math. Statist. Vol. 42, pp. 1328–1338, 1971.
J.B. Moore, "On Strong Consistence of Least Square Identification Algorithm," Automatica, Vol. 14, pp. 505–509, 1978.
V. Strejc, "Least Square Parameter Estimation," Automatica, Vol. 16, pp. 535–550, 1980.
B. Widrow, P.E. Mantey, L.J. Griffiths and B.B. Good, "Adaptive Antenna Systems," Proc. IEEE, Vol. 55, pp. 2143–2159, 1967.
J.P. Burg, "A New Analysis Technique for time Series Data," Presented at the 37th Annual Meeting Soc. Explor. Geophr., Oklahoma City, Okla., 1967.
A. van den Bos, "Alternative Intepretation of Maximum Entropy Spectral Analysis," IEEE Trans. Inform. Theory, Vol. IT-17, pp. 493–494, 1971.
H. Akaike, "A New Look at the Statistical Model Identification," IEEE Trans. Automat. Contr., AC-19, pp. 716–723, 1974.
C. Tsai and L. Kurz, "A Practical Approach to Robust Recusive Estimation/Detection and Its Application to Spread Spectrum Communications," Submitted to IEEE Trans. Inform. Theory.
C. Tsai, "A Contribution to Robust Detection and Estimation," Ph.D. Thesis, Polytechnic Institute of New York.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1982 Springer-Verlag
About this paper
Cite this paper
Tsai, C., Kurz, L. (1982). A robustized maximum entropy approach to system identification. In: Drenick, R.F., Kozin, F. (eds) System Modeling and Optimization. Lecture Notes in Control and Information Sciences, vol 38. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0006145
Download citation
DOI: https://doi.org/10.1007/BFb0006145
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-11691-2
Online ISBN: 978-3-540-39459-4
eBook Packages: Springer Book Archive