Exploring the segmentation space for the assessment of multiple change-point models

Yann Guédon 1, 2
1 VIRTUAL PLANTS - Modeling plant morphogenesis at different scales, from genes to phenotype
CRISAM - Inria Sophia Antipolis - Méditerranée , INRA - Institut National de la Recherche Agronomique, Centre de coopération internationale en recherche agronomique pour le développement [CIRAD] : UMR51
Abstract : This paper addresses the retrospective or off-line multiple change-point detection problem. Methods for exploring the space of possible segmentations of a sequence for a fixed number of change points may be divided into two categories: (i) enumeration of segmentations, (ii) summary of the possible segmentations in change-point or segment profiles. Concerning the first category, a forward dynamic programming algorithm for computing the top L most probable segmentations and a forward-backward algorithm for sampling segmentations are derived. Concerning the second category, a forward-backward dynamic programming algorithm and a smoothing-type forward-backward algorithm for computing two types of change-point and segment profiles are derived. The proposed methods are mainly useful for exploring the space of possible segmentations for successive numbers of change points and provide a set of assessment tools for multiple change-point models. We show using examples that the proposed methods may help to compare alternative multiple change-point models (e.g. Gaussian model with piecewise constant variances or global variance), predict supplementary change points, highlight overestimation of the number of change points and summarize the uncertainty concerning the location of change points.
Type de document :
Rapport
[Research Report] RR-6619, INRIA. 2008, pp.37
Liste complète des métadonnées


https://hal.inria.fr/inria-00311634
Contributeur : Yann Guédon <>
Soumis le : mardi 19 août 2008 - 16:59:03
Dernière modification le : samedi 27 janvier 2018 - 01:31:25
Document(s) archivé(s) le : vendredi 5 octobre 2012 - 11:48:24

Fichiers

RR-6619.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00311634, version 1

Collections

Citation

Yann Guédon. Exploring the segmentation space for the assessment of multiple change-point models. [Research Report] RR-6619, INRIA. 2008, pp.37. 〈inria-00311634〉

Partager

Métriques

Consultations de la notice

487

Téléchargements de fichiers

354