MAP segmentation in Bayesian hidden Markov models a case study

MAP segmentation in Bayesian hidden Markov models : a case study

© 2020 Informa UK Limited, trading as Taylor & Francis Group.

Bibliographische Detailangaben
Veröffentlicht in:Journal of applied statistics. - 1991. - 49(2022), 5 vom: 09., Seite 1203-1234
1. Verfasser: Koloydenko, Alexey (VerfasserIn)
Weitere Verfasser: Kuljus, Kristi, Lember, Jüri
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:Journal of applied statistics
Schlagworte:Journal Article Bayesian inference EM algorithm Hidden Markov model MAP sequence viterbi algorithm
Beschreibung
Zusammenfassung:© 2020 Informa UK Limited, trading as Taylor & Francis Group.
We consider the problem of estimating the maximum posterior probability (MAP) state sequence for a finite state and finite emission alphabet hidden Markov model (HMM) in the Bayesian setup, where both emission and transition matrices have Dirichlet priors. We study a training set consisting of thousands of protein alignment pairs. The training data is used to set the prior hyperparameters for Bayesian MAP segmentation. Since the Viterbi algorithm is not applicable any more, there is no simple procedure to find the MAP path, and several iterative algorithms are considered and compared. The main goal of the paper is to test the Bayesian setup against the frequentist one, where the parameters of HMM are estimated using the training data
Beschreibung:Date Revised 16.07.2022
published: Electronic-eCollection
Citation Status PubMed-not-MEDLINE
ISSN:0266-4763
DOI:10.1080/02664763.2020.1858273