Estimating hidden semi-markov chains from discrete sequences

Guédon Yann. 2003. Estimating hidden semi-markov chains from discrete sequences. Journal of Computational and Graphical Statistics, 12 (3) : 604-639.

Résumé : This article addresses the estimation of hidden semi-Markov chains from non stationary discrete sequences. Hidden semi-Markov chains are particularly useful to model the succession of homogeneous zones or segments along sequences. A discrete hidden semi-Markov s chain is composed of a non observable state process, which is a semi-Markov chain, and a discrete output process. Hidden semi-Markov chains generalize hidden Markov chains and enable the modeling of various durational structures. From an algorithmic point of view, a new forward-backward algorithm is proposed whose complexity is similar to that of the Viterbi algorithm in terms of sequence length (quadratic in the worst case in time and linear in space). This opens the way to the maximum likelihood estimation of hidden semi-Markov chains from long sequences. This statistical modeling approach is illustrated by the analysis of branching and flowering patterns in plants.

Mots-clés Agrovoc : modèle mathématique, modèle de simulation, ramification, floraison, modèle végétal, Prunus armeniaca

Mots-clés complémentaires : Architecture végétale, Biomodélisation, Algorithme

Classification Agris : U10 - Informatique, mathématiques et statistiques
F50 - Anatomie et morphologie des plantes
F62 - Physiologie végétale - Croissance et développement

Auteurs et affiliations

• Guédon Yann, CIRAD-AMIS-AMAP (FRA)

Source : Cirad - Agritrop (https://agritrop.cirad.fr/529866/)

Métriques

[ Page générée et mise en cache le 2024-12-23 ]