Adaptive estimation of hidden nearly completely decomposable Markov chains

TitleAdaptive estimation of hidden nearly completely decomposable Markov chains
Publication TypeConference Paper
Year of Publication1994
AuthorsKrishnamurthy, V.
Conference NameAcoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on
PaginationIV/337 -IV/340 vol.4
Date Publishedapr.
Keywordsadaptive equalisers, adaptive estimation, adaptive signal processing, aggregation techniques, computational costs, estimation algorithms, expectation maximization algorithm, FIR filters, Gaussian noise, hidden Markov model, hidden Markov models, hidden nearly completely decomposable Markov chains, maximum likelihood estimation, maximum-likelihood estimation schemes, optimisation, state estimation, stochastic complementation, white Gaussian noise, white noise
Abstract

We propose maximum-likelihood (ML) estimation schemes for nearly completely decomposable Markov chains (NCDMC) in white Gaussian noise. Aggregation techniques based on stochastic complementation are applied to reduce the dimension of the resulting hidden Markov model (HMM) and hence substantially reduce the computational costs of the estimation algorithms. We then present an aggregation based expectation maximization (EM) algorithm for estimating the parameters and states of the HMM

URLhttp://dx.doi.org/10.1109/ICASSP.1994.389811
DOI10.1109/ICASSP.1994.389811

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
Email:

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