Bayesian approximations to hidden semi-Markov models for telemetric monitoring of physical activity

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Hadj-Amar, Beniamino
• dc.contributor.author Jewson, Jack
• dc.contributor.author Fiecas, Mark
• dc.date.accessioned 2023-06-27T07:02:07Z
• dc.date.available 2023-06-27T07:02:07Z
• dc.date.issued 2023
• dc.description.abstract We propose a Bayesian hidden Markov model for analyzing time series and sequential data where a special structure of the transition probability matrix is embedded to model explicit-duration semi-Markovian dynamics. Our formulation allows for the development of highly flexible and interpretable models that can integrate available prior information on state durations while keeping a moderate computational cost to perform efficient posterior inference. We show the benefits of choosing a Bayesian approach for HSMM estimation over its frequentist counterpart, in terms of model selection and out-of-sample forecasting, also highlighting the computational feasibility of our inference procedure whilst incurring negligible statistical error. The use of our methodology is illustrated in an application relevant to e-Health, where we investigate rest-activity rhythms using telemetric activity data collected via a wearable sensing device. This analysis considers for the first time Bayesian model selection for the form of the explicit state dwell distribution. We further investigate the inclusion of a circadian covariate into the emission density and estimate this in a data-driven manner.
• dc.format.mimetype application/pdf
• dc.identifier.citation Hadj-Amar B, Jewson J, Fiecas M. Bayesian approximations to hidden semi-Markov models for telemetric monitoring of physical activity. Bayesian Anal. 2023;18(2):547-77. DOI: 10.1214/22-ba1318
• dc.identifier.doi http://dx.doi.org/10.1214/22-ba1318
• dc.identifier.issn 1936-0975
• dc.identifier.uri http://hdl.handle.net/10230/57372
• dc.language.iso eng
• dc.publisher International Society for Bayesian Analysis
• dc.relation.ispartof Bayesian Analysis. 2023;18(2):547-77.
• dc.rights © 2023 International Society for Bayesian Analysis. This publication is under a Creative Commons Attribution 4.0 International License.
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri http://creativecommons.org/licenses/by/4.0/
• dc.subject.keyword Markov switching process
• dc.subject.keyword Hamiltonian Monte Carlo
• dc.subject.keyword Bayes factor
• dc.subject.keyword telemetric activity data
• dc.subject.keyword circadian rhythm
• dc.title Bayesian approximations to hidden semi-Markov models for telemetric monitoring of physical activity
• dc.type info:eu-repo/semantics/article
• dc.type.version info:eu-repo/semantics/publishedVersion