zbMATH — the first resource for mathematics

A view on filtering of continuous data signals. (English) Zbl 0783.93101
A spline approximation for continuous signals, and piecewise continuous signals, is employed. Bayesian identification is used to determine the parameters. The conditions on the smoothness of the approximation are introduced in the form of prior information about the parameters through, so called, fictitious data. The approximation permits differentiation of filtered signals.
93E11 Filtering in stochastic control theory
62C10 Bayesian problems; characterization of Bayes procedures
94A12 Signal theory (characterization, reconstruction, filtering, etc.)
41A15 Spline approximation
Full Text: Link EuDML
[1] C. De Boor: A Practical Guide to Splines. Springer-Verlag, Berlin - Heidelberg - New York 1978. · Zbl 0406.41003
[2] M. Kárný: A note on feeding uncertain knowledge into recursive least squares. Proc. 30th CDC, Brighton, U.K., 1991.
[3] M. Kárný I. Nagy J. Böhm, A. Halousková: Design of spline-based self-tuners. Kybernetika 26 (1990), 1, 17-30. · Zbl 0712.93030
[4] M. Kárný A. Halousková, I.Nagy: Modelling, identification and adaptive control of crossdirection basis weight of paper sheets. Internat. Conf. CONTROL 88, Oxford 1988, pp. 159-164.
[5] R. Kohn, G. Ansley: Equivalence between Bayesian smoothness priors and optimal smoothning for function estimation. Bayesian Analysis of Time Series and Dynamic Models (J. C. Spall, Marcel Dekker, New York 1988, pp. 393-430.
[6] N. P. Kornejčuk: Splajny v teorii aproximacii. Nauka, Moskva 1984.
[7] L. Ljung, T. Söderström: Theory and Practice of Recursive Identification. MIT Press, Mass. 1983. · Zbl 0548.93075
[8] V. Peterka: Bayesian approach to system identification. Trends and Progress in System Identification (P. Eykhoff, Pergamon Press, Oxford 1981, pp. 239-304. · Zbl 0451.93059
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.