V
Vincent Brault
Researcher at Département de Mathématiques
Publications - 37
Citations - 360
Vincent Brault is an academic researcher from Département de Mathématiques. The author has contributed to research in topics: Matrix (mathematics) & Biclustering. The author has an hindex of 10, co-authored 36 publications receiving 277 citations. Previous affiliations of Vincent Brault include University of Paris-Sud & Université Paris-Saclay.
Papers
More filters
Journal ArticleDOI
Estimation and selection for the latent block model on categorical data
TL;DR: Estimation procedures and model selection criteria derived for binary data are generalised and an exact expression of the integrated completed likelihood criterion requiring no asymptotic approximation is derived.
Journal ArticleDOI
Using gaze behavior to gain insights into the impacts of naturalness on city dwellers' perceptions and valuation of a landscape
Marylise Cottet,Lise Vaudor,Hervé Tronchère,Dad Roux-Michollet,Marie Augendre,Vincent Brault +5 more
TL;DR: In this paper, the authors used in situ captured data (eye-tracking data acquired with a mobile device) to study the influences of landscape composition on the landscape perceptions and valuations of city dwellers.
Journal ArticleDOI
Group testing as a strategy for COVID-19 epidemiological monitoring and community surveillance.
TL;DR: An analysis and applications of sample pooling to the epidemiologic monitoring of COVID-19 with an economy of tests and a method for the measure of the prevalence in a population, based on group testing, taking into account the increased number of false negatives associated to this method.
Model selection for the binary latent block model
TL;DR: The comparison of a determinist approach using a variational principle with a stochastic approach with a MCMC algorithm is first discussed and applied in the context of binary data to build and compute ICL and BIC criteria for model selection.
Journal ArticleDOI
Comparing high-dimensional partitions with the Co-clustering Adjusted Rand Index
TL;DR: A new criterion based on the Adjusted Rand Index is developed and is called the Co-clusteringadjusted Rand Index named CARI, which suggests new improvements to existing criteria such as the classification error which counts the proportion of misclassified cells and the Extended Normalized Mutual Information criterion.