Linear Filtering and State Space Representations of Hidden Markov Models
(2002) In Preprints in Mathematical Sciences- Abstract
- The topic of this paper is linear filtering of hidden Markov models (HMMs) and linear innovation form representations of HMMs. The possibility to represent the widely used HMM as a state space model is interesting in its own respect, but our interest also comes from subspace estimation methods. To be able to fit the HMM into the framework of subspace methods the process needs to be formulated in state space form. This reformulation is complicated by the non-minimality within the state space representation of the HMM. The reformulation involves deriving solutions to algebraic Riccati equations which are usually treated under minimality assumptions.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/829857
- author
- Andersson, Sofia LU ; Rydén, Tobias LU and Johansson, Rolf LU
- organization
- publishing date
- 2002
- type
- Book/Report
- publication status
- published
- subject
- in
- Preprints in Mathematical Sciences
- issue
- 2002:5
- publisher
- Center for Mathematical Sceinces, Lund University
- report number
- LUTFMS-5019-2002
- language
- English
- LU publication?
- yes
- id
- fbf317aa-2a73-4b0f-9de1-b53866c01454 (old id 829857)
- date added to LUP
- 2016-04-04 09:34:36
- date last changed
- 2023-09-14 15:16:17
@techreport{fbf317aa-2a73-4b0f-9de1-b53866c01454, abstract = {{The topic of this paper is linear filtering of hidden Markov models (HMMs) and linear innovation form representations of HMMs. The possibility to represent the widely used HMM as a state space model is interesting in its own respect, but our interest also comes from subspace estimation methods. To be able to fit the HMM into the framework of subspace methods the process needs to be formulated in state space form. This reformulation is complicated by the non-minimality within the state space representation of the HMM. The reformulation involves deriving solutions to algebraic Riccati equations which are usually treated under minimality assumptions.}}, author = {{Andersson, Sofia and Rydén, Tobias and Johansson, Rolf}}, institution = {{Center for Mathematical Sceinces, Lund University}}, language = {{eng}}, number = {{LUTFMS-5019-2002}}, series = {{Preprints in Mathematical Sciences}}, title = {{Linear Filtering and State Space Representations of Hidden Markov Models}}, year = {{2002}}, }