Funclust: a curves clustering method using ...
Type de document :
Article dans une revue scientifique
URL permanente :
Titre :
Funclust: a curves clustering method using functional random variables density approximation
Auteur(s) :
Titre de la revue :
Neurocomputing
Numéro :
112
Pagination :
164-171
Éditeur :
Elsevier
Date de publication :
2013
ISSN :
0925-2312
Mot(s)-clé(s) :
Functional data
Model-based clustering
Random variable density
Functional principal component analysis
Model-based clustering
Random variable density
Functional principal component analysis
Discipline(s) HAL :
Mathématiques [math]/Statistiques [math.ST]
Résumé en anglais : [en]
A new method for clustering functional data is proposed under the name Funclust. This method relies on the approximation of the notion of probability density for functional random variables, which generally does not exists. ...
Lire la suite >A new method for clustering functional data is proposed under the name Funclust. This method relies on the approximation of the notion of probability density for functional random variables, which generally does not exists. Using the Karhunen-Loeve expansion of a stochastic process, this approximation leads to define an approximation for the density of functional variables. Based on this density approximation, a parametric mixture model is proposed. The parameter estimation is carried out by an EM-like algorithm, and the maximum a posteriori rule provides the clusters. The efficiency of Funclust is illustrated on several real datasets, as well as for the characterization of the Mars surface.Lire moins >
Lire la suite >A new method for clustering functional data is proposed under the name Funclust. This method relies on the approximation of the notion of probability density for functional random variables, which generally does not exists. Using the Karhunen-Loeve expansion of a stochastic process, this approximation leads to define an approximation for the density of functional variables. Based on this density approximation, a parametric mixture model is proposed. The parameter estimation is carried out by an EM-like algorithm, and the maximum a posteriori rule provides the clusters. The efficiency of Funclust is illustrated on several real datasets, as well as for the characterization of the Mars surface.Lire moins >
Langue :
Anglais
Audience :
Internationale
Vulgarisation :
Non
Établissement(s) :
CNRS
Université de Lille
Université de Lille
Date de dépôt :
2020-06-08T14:11:28Z