Adaptive non-linear time-series estimation based on hidden Markov models

TitleAdaptive non-linear time-series estimation based on hidden Markov models
Publication TypeConference Paper
Year of Publication1993
AuthorsKrishnamurthy, V.
Conference NameDecision and Control, 1993., Proceedings of the 32nd IEEE Conference on
Pagination720 -725 vol.1
Date Publisheddec.
Keywordsadaptive nonlinear time-series estimation, ARMAX systems, finite-state Markov chain, gradient based scheme, hidden Markov models, maximum likelihood estimation, maximum-likelihood estimation schemes, ML model estimates, nonlinear systems, online estimation, parameter estimation, recursive EM algorithm, recursive expectation maximization algorithm, sequential estimation, state estimation, time series

In this paper we propose maximum-likelihood (ML) estimation schemes for the parameters and states of ARMAX systems when the input is a finite-state Markov chain. Such models have applications in econometrics, speech processing, communication systems and neuro-biological signal processing. We derive the ML model estimates using the expectation maximization (EM) algorithm. We then develop two sequential or ldquo;online rdquo; estimation schemes: Recursive EM algorithm and a gradient based scheme


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