Linear adaptive filtering of random sequences on basis of deterministic approach
Abstract
The article studies the technique of synthesis of random sequence filters with unknown prior statistical information about the parameters of signal and noises. The synthesis uses only current measurements and a limited amount of empirical information, which leads to the necessity of using a deterministic approach based on the least squares method. In order to obtain a recursive filtering algorithm, it is proposed to extend the structure of the method loss function by including in loss function an additional term that defines the estimate extrapolation for the next measurement period. The optimal current estimate is based on both measurement results and extrapolated values. The extrapolation function is selected based on the desired class of synthesized filter. The paper considers a variant of polynomial extrapolation, taking into account previous estimates and measurements. The use of only previous estimates leads to the structure of the filter with feedback, while the use of only the previous measurements forms a transversal filter. Mathematical modeling was carried out and on particular example and the loss of filtering accuracy by not taking into account a priori statistical information was estimated.
About the Authors
V. A. Artemiev
Institute of Applied Physics of the National Academy of Sciences of Belarus
Valentin M. Artemiev – Corresponding Member of the National Academy of Sciences of Belarus, D. Sc. (Engineering), Professor, Chief Researcher.
16, Akademicheskaya Str., 220072, Minsk
A. O. Naumov
Institute of Applied Physics of the National Academy of Sciences of Belarus
Russian Federation
Russian Federation
Alexander O. Naumov – Ph. D. (Physics and Mathematics), Head of Laboratory.
16, Akademicheskaya Str., 220072, Minsk
L. L. Kokhan
Institute of Applied Physics of the National Academy of Sciences of Belarus
Leonid L. Kokhan – Ph. D. (Engineering), Senior Researcher.
16, Akademicheskaya Str., 220072, Minsk
References
1. Haykin S. S. Adaptive Filter Theory. N.J., Prentice-Hall, 2002, 936 p.
2. Fomin V. M. Rekurrentnoe otsenivanie i adaptivnaya fil’tratsiya. Recurrent Estimation and Adaptive Filtering. Moscow, Nauka Publ., 1984, 388 p. (in Russian).
3. Mueller M. S. Least-squares algorithms for adaptive equalizers. The Bell System Technical Journal, 1981, vol. 60, рр. 1905–1925. doi: 10.1002/j.1538-7305.1981.tb00302.x
4. Lev-Ari H., Kailath T., Cioffi J. Least-squares adaptive lattice and transversal filters: A unified geometric theory. IEEE Transactions on Information Theory, 1984, vol. 30, рр. 222–236. doi: 10.1109/tit.1984.1056882
5. Cioffi J. M., Kailath T. Fast, recursive-least-squares transversal filters for adaptive filtering. IEEE Transactions on Acoustics Speech and Signal Processing, 1984, vol. 32, рр. 304–337. doi: 10.1109/tassp.1984.1164334
6. Luk F. T., Qiao S. Analysis of a recursive least-squares signal-processing algorithm. SIAM Journal on Scientific and Statistical Computing, 1989, vol. 10, рр. 407–418. doi: 10.1137/0910027
7. Sayed A. H., Kailath T. A state-space approach to adaptive RLS filtering. IEEE Signal Processing Magazine, 1994, vol. 11, рр. 18–60. doi: 10.1109/79.295229
8. Yang B. A note on the error propagation analysis of recursive least squares algorithms. IEEE Transactions on Signal Processing. 1994, vol. 42, рр. 3523–3525. doi: 10.1109/78.340788
9. Manolakis D. G., Ingle V. K., Kogon S. M. Statistical and Adaptive Signal Processing: Spectral Estimation, Signal Modeling, Adaptive Filtering, and Array Processing. Boston, McGraw-Hill, 2000, 796 p.
10. Artem’ev V. M., Naumov A. O., Kokhan L. L. Lineynaya fil’tratsiya mnogomernykh sluchaynykh posledovatel’nostey rasshirennym metodom naimen’shikh kvadratov [Linear filtering of random sequences using a least squares method with regularization]. Informatika [Informatics], 2016, no. 4(52), pp. 20–25 (in Russian).
11. Artem’ev V. M., Naumov A. O., Kokhan L. L. Nelineynaya fil’tratciya sluchaynykh posledovatel’nostey rasshirennym metodom naimen’shikh kvadratov [Nonlinear filtering of random sequences with extended least-squares method]. Informatika [Informatics], 2018, vol. 15, no. 1, pp. 60–69 (in Russian).
12. Tsypkin Ia. Z. Optimizatsiya v usloviyakh neopredelennosti [Optimization in the conditions of uncertainty]. Doklady AN SSSR [Proc. of the Academy of Sciences of the USSR], 1976, vol. 228, no. 6, pp. 1306–1309 (in Russian).
13. Anderson T. Statisticheskiy analiz vremennykh ryadov. Statistical Analysis of Time Series. Moscow, Mir Publ., 1976, 755 p. (in Russian).
Review
For citations:
Artemiev V.A., Naumov A.O., Kokhan L.L. Linear adaptive filtering of random sequences on basis of deterministic approach. Informatics. 2018;15(3):32-40. (In Russ.)
Views: 617
Email this article 