OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Joint segmentation of piecewise constant autoregressive processes by using a hierarchical model and a Bayesian sampling approach

Dobigeon, Nicolas and Tourneret, Jean-Yves and Davy, Manuel Joint segmentation of piecewise constant autoregressive processes by using a hierarchical model and a Bayesian sampling approach. (2007) IEEE Transactions on Signal Processing, vol. 5 (n° 4). pp. 1251-1263. ISSN 1053-587X

[img]
Preview
(Document in English)

PDF (Publisher's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1158Kb

Official URL: http://dx.doi.org/10.1109/TSP.2006.889090

Abstract

We propose a joint segmentation algorithm for piecewise constant autoregressive (AR) processes recorded by several independent sensors. The algorithm is based on a hierarchical Bayesian model. Appropriate priors allow to introduce correlations between the change locations of the observed signals. Numerical problems inherent to Bayesian inference are solved by a Gibbs sampling strategy. The proposed joint segmentation methodology yields improved segmentation results when compared to parallel and independent individual signal segmentations. The initial algorithm is derived for piecewise constant AR processes whose orders are fixed on each segment. However, an extension to models with unknown model orders is also discussed. Theoretical results are illustrated by many simulations conducted with synthetic signals and real arc-tracking and speech signals.

Item Type:Article
Additional Information:This publication is available on http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=78
Audience (journal):International peer-reviewed journal
Uncontrolled Keywords:
Institution: Université de Toulouse > Institut National Polytechnique de Toulouse - INPT
Université de Toulouse > Université Paul Sabatier-Toulouse III - UPS
French research institutions > Centre National de la Recherche Scientifique - CNRS
Other partners > Ecole Centrale de Lille (FRANCE)
Other partners > Université des Sciences et Technologies de Lille - USTL (FRANCE)
Laboratory name:
Statistics:download
Deposited By:Jean-yves TOURNERET

Repository Staff Only: item control page