Cargando…

Bayesian Model Search for Nonstationary Periodic Time Series

We propose a novel Bayesian methodology for analyzing nonstationary time series that exhibit oscillatory behavior. We approximate the time series using a piecewise oscillatory model with unknown periodicities, where our goal is to estimate the change-points while simultaneously identifying the poten...

Descripción completa

Detalles Bibliográficos
Autores principales: Hadj-Amar, Beniamino, Rand, Bärbel Finkenstädt, Fiecas, Mark, Lévi, Francis, Huckstepp, Robert
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Taylor & Francis 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7984273/
https://www.ncbi.nlm.nih.gov/pubmed/33814652
http://dx.doi.org/10.1080/01621459.2019.1623043
Descripción
Sumario:We propose a novel Bayesian methodology for analyzing nonstationary time series that exhibit oscillatory behavior. We approximate the time series using a piecewise oscillatory model with unknown periodicities, where our goal is to estimate the change-points while simultaneously identifying the potentially changing periodicities in the data. Our proposed methodology is based on a trans-dimensional Markov chain Monte Carlo algorithm that simultaneously updates the change-points and the periodicities relevant to any segment between them. We show that the proposed methodology successfully identifies time changing oscillatory behavior in two applications which are relevant to e-Health and sleep research, namely the occurrence of ultradian oscillations in human skin temperature during the time of night rest, and the detection of instances of sleep apnea in plethysmographic respiratory traces. Supplementary materials for this article are available online.