Change-point detection in astronomical data by using a hierarchical model and a bayesian sampling approach

Author

Dobigeon, Nicolas ; Tourneret, Jean-Yves ; Scargle, Jeffrey D.

Author_Institution

IRIT/ENSEEIHT/TeSA, Toulouse

fYear

2005

fDate

17-20 July 2005

Firstpage

369

Lastpage

374

Abstract

Detection of significant intensity variations in astronomical time-series can be achieved with 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 with real and synthetic photon counting data illustrate the performance of the proposed algorithm. An extension to joint segmentation of multiple time series is also discussed

Keywords

Bayes methods; parameter estimation; piecewise constant techniques; signal detection; signal sampling; stochastic processes; time series; Gibbs sampling strategy; astronomical data; change-point detection; hierarchical Bayesian sampling approach; hyperparameter estimation; multiple time series; parameter estimation; photon counting data; piecewise constant Poisson rate model; Bayesian methods; Image sampling; Image segmentation; Inference algorithms; Iterative algorithms; Maximum likelihood detection; Maximum likelihood estimation; NASA; Parameter estimation; Sampling methods;

fLanguage

English

Publisher

ieee

Conference_Titel

Statistical Signal Processing, 2005 IEEE/SP 13th Workshop on

Conference_Location

Novosibirsk

Print_ISBN

0-7803-9403-8

Type

conf

DOI

10.1109/SSP.2005.1628623

Filename

1628623