Gaussian-Based Visualization of Gaussian ...
Type de document :
Article dans une revue scientifique: Article original
URL permanente :
Titre :
Gaussian-Based Visualization of Gaussian and Non-Gaussian-Based Clustering
Auteur(s) :
Biernacki, Christophe [Auteur]
Laboratoire Paul Painlevé - UMR 8524 [LPP]
Marbac, Matthieu [Auteur]
Université de Rennes [UR]
Vandewalle, Vincent [Auteur]
METRICS : Evaluation des technologies de santé et des pratiques médicales - ULR 2694

Laboratoire Paul Painlevé - UMR 8524 [LPP]
Marbac, Matthieu [Auteur]
Université de Rennes [UR]
Vandewalle, Vincent [Auteur]

METRICS : Evaluation des technologies de santé et des pratiques médicales - ULR 2694
Titre de la revue :
Journal of Classification
Nom court de la revue :
J. Classif.
Numéro :
38
Pagination :
129–157
Date de publication :
2020-07-25
ISSN :
0176-4268
Mot(s)-clé(s) en anglais :
Visualization
Model-based clustering
Linear discriminant analysis
Factorial analysis
Gaussian mixture
Dimension reduction
Model-based clustering
Linear discriminant analysis
Factorial analysis
Gaussian mixture
Dimension reduction
Discipline(s) HAL :
Sciences du Vivant [q-bio]
Résumé en anglais : [en]
A generic method is introduced to visualize in a “Gaussian-like way,” and onto , results of Gaussian or non-Gaussian–based clustering. The key point is to explicitly force a visualization based on a spherical Gaussian ...
Lire la suite >A generic method is introduced to visualize in a “Gaussian-like way,” and onto , results of Gaussian or non-Gaussian–based clustering. The key point is to explicitly force a visualization based on a spherical Gaussian mixture to inherit from the within cluster overlap that is present in the initial clustering mixture. The result is a particularly user-friendly drawing of the clusters, providing any practitioner with an overview of the potentially complex clustering result. An entropic measure provides information about the quality of the drawn overlap compared with the true one in the initial space. The proposed method is illustrated on four real data sets of different types (categorical, mixed, functional, and network) and is implemented on the r package ClusVis.Lire moins >
Lire la suite >A generic method is introduced to visualize in a “Gaussian-like way,” and onto , results of Gaussian or non-Gaussian–based clustering. The key point is to explicitly force a visualization based on a spherical Gaussian mixture to inherit from the within cluster overlap that is present in the initial clustering mixture. The result is a particularly user-friendly drawing of the clusters, providing any practitioner with an overview of the potentially complex clustering result. An entropic measure provides information about the quality of the drawn overlap compared with the true one in the initial space. The proposed method is illustrated on four real data sets of different types (categorical, mixed, functional, and network) and is implemented on the r package ClusVis.Lire moins >
Langue :
Anglais
Audience :
Internationale
Vulgarisation :
Non
Établissement(s) :
Université de Lille
CHU Lille
CHU Lille
Date de dépôt :
2023-11-15T09:43:46Z
2023-12-18T09:41:30Z
2023-12-18T09:41:30Z