Parcourir HE en Hainaut par type de document "Article scientifique"
Voici les éléments 1-11 de 11
-
Analyse de malwares et classification à l’aide de réseaux de neurones convolutionnels 1D
2021, HE en HainautArticle scientifiqueLes logiciels malveillants peuvent avoir des impacts particulièrement négatifs sur notre société, d’autant plus que celle-ci a de plus en plus recours à des systèmes informatiques. En vue de garantir la sécurité de ces systèmes, la détection et la prévention de ces logiciels malveillants sont nécessaires. Dans cette optique, l’objectif de ce travail est de procéder à une classification entre des ... -
Comparaison des frameworks d’apprentissage profond
2021, HE en HainautArticle scientifiqueL’apprentissage automatique est un ensemble de méthodes issues de l’intelligence artificielle qui visent à apprendre à l’aide de données. Au sein de ces méthodes, l’apprentissage profond se concentre sur des réseaux de neurones qui sont des modèles mathématiques dont l’objectif est de s’inspirer du fonctionnement du cerveau à l’aide de neurones artificiels. Ceux-ci sont très performants lorsqu’il ... -
Cross-biome comparison of microbial association networks
2015, AutreArticle scientifiqueClinical and environmental meta-omics studies are accumulating an ever-growing amount of microbial abundance data over a wide range of ecosystems. With a sufficiently large sample number, these microbial communities can be explored by constructing and analyzing co-occurrence networks, which detect taxon associations from abundance data and can give insights into community structure. Here, we investigate ... -
Distributed Deep Learning: From Single-Node to Multi-Node Architecture
2022, HE en HainautArticle scientifiqueDuring the last years, deep learning (DL) models have been used in several applications with large datasets and complex models. These applications require methods to train models faster, such as distributed deep learning (DDL). This paper proposes an empirical approach aiming to measure the speedup of DDL achieved by using different parallelism strategies on the nodes. Local parallelism is considered ... -
Efficiency of GPUs for Relational Database Engine Processing
2016, HE en HainautAutreArticle scientifiqueRelational database management systems (RDBMS) are still widely required by numerous business applications. Boosting performances without compromising functionalities represents a big challenge. To achieve this goal, we propose to boost an existing RDBMS by making it able to use hardware architectures with high memory bandwidth like GPUs. In this paper we present a solution named CuDB. We compare ... -
Improving Performances of an Embedded Relational Database Management System with a Hybrid CPU/GPU Processing Engine
2017, HE en HainautAutreArticle scientifiqueEnd-user systems are increasingly impacted by the exponential growth of data volumes and their processing. Moreover, post-processing operations, essentially dedicated to ergonomic features, require more and more resources. Improving overall performances of embedded relational database management systems (RDBMS) can contribute to deliver better responsiveness of end-user systems while increasing the ... -
Intracellular Pathways of Holothuroid Oocyte Maturation Induced by the Thioredoxin Trx-REES
2021, HE en HainautArticle scientifiqueAbstract: In holothuroids, oocyte maturation is stopped in ovaries at the prophase I stage of meiosis. In natural conditions, the blockage is removed during the spawning by an unknown mechanism. When oocytes are isolated by dissection, the meiotic release can be successfully induced by a natural inducer, the REES (i.e., Rough Extract of Echinoid Spawn) that is used in aquaculture to obtain ... -
Les invectives cicéroniennes comme matrices des invectives de l'époque triumvirale. Le cas des Philippiques I et II
01 février 2024, HE en HainautArticle scientifiqueArticle scientifique publié dans une revue spécialisée en sciences de l'Antiquité avec procédure de peer-review. -
NAO,un nouvel outil d'aide à la gestion de classe
mai 2021, HE en HainautArticle scientifiquePlusieurs études ont montré que ces robots sont de potentiels outils éducatifs, en particulier auprès d’élèves ayant des difficultés d'apprentissage. Parmi les robots, il existe les robots humanoïdes qui peuvent induire une expérience différente de l'apprentissage, passant d'un objet à manipuler à émergence de situations sociales et d’interaction à valence psychoaffective. -
Single node deep learning frameworks: Comparative study and CPU/GPU performance analysis
2021, HE en HainautArticle scientifiqueDeep learning presents an efficient set of methods that allow learning from massive volumes of data using complex deep neural networks. To facilitate the design and implementation of algorithms, deep learning frameworks provide a high-level programming interface. Based on these frameworks, new models, and applications are able to make better and better predictions. One type of deep learning application ... -
Thioredoxins induce oocyte maturation in holothuroids (Echinodermata)
15 juillet 2019, HE en HainautArticle scientifiqueChromatographic fractions of a rough extract of echinoid spawn (REES) is demonstrated to efficiently induce oocyte maturation in aspidochirote holothuroids. The method is so efficient that it is currently used in holothuriculture to obtain fertilised eggs even outside the reproductive period of the aquacultivated species. In the present study, we isolated and identified from echinoid spawns the ...