Abstract
In this paper, we outline an intrinsic formulation of the identification problem of linear system theory. The nonlinear filtering problems which appear in this way essentially fall into four distinct classes, distinguished by their estimation algebra. In principle, it is possible to explicitly solve the identification problem in the ‘hyperbolic cases’ using classical methods from the theory of partial differential equations. This is illustrated by an example which indicates the required sufficient statistics for solving the identification problem.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
H.J. Kushner, “Dynamical Equations for Optimal nonlinear filtering”, J. Differential Equations, Vol. 3, 1967, pp. 179–190.
H.J. Kushner, “On the differential equations satisfied by conditional probability densities of Markov processes, with applications,” RIAS Tech. Report No. 64-6, March 1964.
R.W. Brockett and J.M.C. Clark, “The geometry of the conditional density equation,” Proc. of the Oxford Conference on Stochastic Systems, Oxford, England, 1978.
S.K. Mitter, “On the analogy between mathematical problems of nonlinear filtering and quantum physics,” Richerche di Automatica, 1980.
E. Pardoux, “Stochastic partial differential equations and filtering of diffusion processes,” Stochastics, Vol. 3, 1979, pp. 127–167.
R.W. Brockett, “Classification and equivalence in estimation theory,” Proc. IEEE Conference on Decision and Control, Dec. 1979, Ft. Lauderdale.
T.T. Kadota and L.A. Shepp, “Conditions for absolute continuity between a certain pair of probability measures,” Z. Wahrscheinlichkeitstheorie und Verw. Gebiete, 16, (1970) pp. 250–260.
T. Kailath and M. Zakai, “Absolute Continuity and Radon- Nikodym derivatives for certain measures relative to the Wiener measure”, Ann. of Math. Statistics, 42 (1971), pp. 130–140.
G. Picci, “Some connections between the theory of sufficient statistics and the identifiability problem,” SIAM J. Appl. Math., Vol. 33, No. 3, 1977, pp. 383–398.
H. Hazewinkel and S.I. Marcus, “On the relationship between Lie algebras and nonlinear estimation,” Proc. of the IEEE Conference on Decision and Control, Dec. 1980, Albuquerque.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1981 D. Reidel Publishing Company
About this paper
Cite this paper
Krishnaprasad, P.S., Marcus, S.I. (1981). Some Nonlinear Filtering Problems Arising in Recursive Identification. In: Hazewinkel, M., Willems, J.C. (eds) Stochastic Systems: The Mathematics of Filtering and Identification and Applications. NATO Advanced Study Institutes Series, vol 78. Springer, Dordrecht. https://doi.org/10.1007/978-94-009-8546-9_16
Download citation
DOI: https://doi.org/10.1007/978-94-009-8546-9_16
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-009-8548-3
Online ISBN: 978-94-009-8546-9
eBook Packages: Springer Book Archive