Abstract
A new formulation of prediction of the values of a random process generated by white noise passing through a linear filter was discussed. It was assumed that observations were carried out in an unknown irregular constrained noise and the coefficients of signal transformation in the observation channel were unknown random variables. A randomized variant of the linear predicting filter which, under certain conditions, is superior to the minimax algorithms was proposed.
Similar content being viewed by others
REFERENCES
Kolmogorov, A.N., Interpolation and Extrapolation of Stationary Random Sequences, Izv.Akad.Nauk SSSR, Mat., 1941, no. 5, pp. 3–14.
Busy, R.S. and Kalman, R.E., New Results in Linear Filtering and Prediction Theory, J.Basic.Eng.ASME, 1961, vol. 83, no. 1, pp. 95–108.
Fomin, V.N., Rekurrentnoe otsenivanie i adaptivnaya fil'tratsiya (Recurrent Estimation and Adaptive Filtering), Moscow: Nauka, 1984.
Digailova, I.A. and Kurzhanski, A.B., The State Estimation Problem under Mixed Uncertainty, Proc.5th IFAC Sympos.NOLCOS'01, St. Petersburg, 2001, p. 584.
Granichin, O.N., Estimating the Parameters of Linear Regression in an Arbitrary Noise, Avtom.Telemekh., 2002, no. 1, pp. 30–41.
Granichin, O.N., Randomized Algorithms of Stochastic Approximation in Arbitrary Noise, Avtom.Telemekh., 2002, no. 2, pp. 44–55.
Guo, L., Ljung, L., and Wang, G-J., Necessary and Sufficient Conditions for Stability of LMS, IEEE Trans.Automat.Control, 1997, vol. 42, no. 6, pp. 761–770.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Granichin, O.N. Nonminimax Filtering in Unknown Irregular Constrained Observation Noise. Automation and Remote Control 63, 1482–1488 (2002). https://doi.org/10.1023/A:1020090422744
Issue Date:
DOI: https://doi.org/10.1023/A:1020090422744