Bayesian Model Search for Nonstationary Periodic Time Series

A methodology paper with applications in e-Health and sleep research, proposing a Bayesian approach for analyzing nonstationary time series with oscillatory behavior. The method uses a trans-dimensional Markov chain Monte Carlo algorithm to estimate change-points and periodicities. The work is authored by Beniamino Hadj-Amar and is available under an Open Access license.

Use Cases

• Detecting ultradian oscillations in human skin temperature during night rest based on the described methodology.
• Identifying instances of sleep apnea in plethysmographic respiratory traces using the proposed change-point detection.
• Developing Bayesian models for piecewise oscillatory signals with unknown periodicities.
• Benchmarking new algorithms for time series segmentation against the described trans-dimensional MCMC approach.

Strengths

• Methodology is described with specific applications to e-Health and sleep research.
• The paper is published under an Open Access license, facilitating reuse.
• Supplementary materials are available online for further detail.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

paperswithcode

Collection Method

Proposed methodology for analyzing time series, with applications described.