Finite dimensional filters for ML estimation of discrete-time Gauss-Markov models

TitleFinite dimensional filters for ML estimation of discrete-time Gauss-Markov models
Publication TypeConference Paper
Year of Publication1997
AuthorsElliott, R. J., and V. Krishnamurthy
Conference NameDecision and Control, 1997., Proceedings of the 36th IEEE Conference on
Pagination1637 -1642 vol.2
Date Publisheddec.
Keywordscomputational complexity, discrete time systems, discrete-time Gauss-Markov models, econometric modelling, expectation maximization algorithm, filter-based EM algorithm, filtering theory, finite dimensional recursive filters, Gaussian processes, linear dynamical system, linear Gaussian state space systems, Markov processes, maximum likelihood estimates, maximum likelihood estimation, ML estimation, Multidimensional digital filters, multiprocessor system, multisensor signal enhancement, parallel implementation, parallel processing, recursive estimation, recursive filters, speech signals, state-space methods, substantially reduced memory requirements

In this paper we derive a class of finite dimensional recursive filters for linear Gaussian state space systems. These finite dimensional filters can be used with the expectation maximization (EM) algorithm to yield maximum likelihood estimates of the parameters of a linear dynamical system. Important advantages of our filter-based EM algorithm compared with the standard smoother-based EM algorithm include: (i) substantially reduced memory requirements; (ii) ease of parallel implementation on a multiprocessor system. The algorithm has applications in multisensor signal enhancement of speech signals and also econometric modelling


a place of mind, The University of British Columbia

Electrical and Computer Engineering
2332 Main Mall
Vancouver, BC Canada V6T 1Z4
Tel +1.604.822.2872
Fax +1.604.822.5949

Emergency Procedures | Accessibility | Contact UBC | © Copyright 2021 The University of British Columbia