Skip to Main content Skip to Navigation
Journal articles

Joint segmentation of multivariate astronomical time series : bayesian sampling with a hierarchical model

Nicolas Dobigeon 1 Jean-Yves Tourneret 1 Jeffrey Scargle
1 IRIT-SC - Signal et Communications
IRIT - Institut de recherche en informatique de Toulouse
Abstract : Astronomy and other sciences often face the problem of detecting and characterizing structure in two or more related time series. This paper approaches such problems using Bayesian priors to represent relationships between signals with various degrees of certainty, and not just rigid constraints. The segmentation is conducted by using a hierarchical Bayesian approach to a piecewise constant Poisson rate model. A Gibbs sampling strategy allows joint estimation of the unknown parameters and hyperparameters. Results obtained with synthetic and real photon counting data illustrate the performance of the proposed algorithm.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00475973
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Friday, April 23, 2010 - 1:59:53 PM
Last modification on : Friday, November 27, 2020 - 9:36:04 AM

Identifiers

  • HAL Id : hal-00475973, version 1

Citation

Nicolas Dobigeon, Jean-Yves Tourneret, Jeffrey Scargle. Joint segmentation of multivariate astronomical time series : bayesian sampling with a hierarchical model. IEEE Transactions on Signal Processing, Institute of Electrical and Electronics Engineers, 2007, vol. 55 n° 2., 414-423 available on : http://oatao.univ-toulouse.fr/875/2/Tourneret_875.pdf. ⟨hal-00475973⟩

Share

Metrics

Record views

214