Search results for "Automatique"

showing 10 items of 39 documents

Computer-aided-diagnosis for ocular abnormalities from a single color fundus photography with deep learning

2023

Any damage to the retina can lead to severe consequences like blindness. This visual impairment is preventable by early detection of ocular abnormalities. Computer-aided diagnosis (CAD) for ocular abnormalities is built by analyzing retinal imaging modalities, for instance, Color Fundus Photography (CFP). The main objectives of this thesis are to build two CAD models, one to detect the microaneurysms (MAs), the first visible symptom of diabetic retinopathy, and the other for multi-label detection of 28 ocular abnormalities consisting of frequent and rare abnormalities from a single CFP by using deep learning-based approaches. Two methods were proposed for MAs detection: ensemble-based and c…

Apprentissage profondTraitement des imagesAnomalies oculairesImage processingMicroaneurysms detectionOcular abnormalities[INFO.INFO-TS] Computer Science [cs]/Signal and Image ProcessingDétection de microanévrismesDeep learningMulti-Label detectionComputer-Aided-DiagnosisDiagnostic automatiqueDétection multi-Étiquettes
researchProduct

From optimization to algorithmic differentiation: a graph detour

2021

This manuscript highlights the work of the author since he was nominated as "Chargé de Recherche" (research scientist) at Centre national de la recherche scientifique (CNRS) in 2015. In particular, the author shows a thematic and chronological evolution of his research interests:- The first part, following his post-doctoral work, is concerned with the development of new algorithms for non-smooth optimization.- The second part is the heart of his research in 2020. It is focused on the analysis of machine learning methods for graph (signal) processing.- Finally, the third and last part, oriented towards the future, is concerned with (automatic or not) differentiation of algorithms for learnin…

Signaux sur graphesOptimisation convexe[STAT.ML]Statistics [stat]/Machine Learning [stat.ML]High dimensional dataGraph signalsStatistiques en grande dimensionAutomatic differentiation[MATH.MATH-OC] Mathematics [math]/Optimization and Control [math.OC][MATH.MATH-OC]Mathematics [math]/Optimization and Control [math.OC][STAT.ML] Statistics [stat]/Machine Learning [stat.ML]Convex optimizationDifférentiation automatique
researchProduct

A metabolomic study of yeast/bacteria interactions

2015

As a complex microbial ecosystem, wine is a particularly interesting model for studying interactions between microorganisms. Contact-independent interactions (indirect interactions) between the yeast Saccharomyces cerevisae and the lactic acid bacterium Oenococcus oeni have a direct effect on malolactic fermentation (MLF), induction and completion, which is an important factor in wine quality. Yeast strains could be classified as MLF+ phenotype if it usually stimulates the bacterial growth or MLF- in the opposite case. The known metabolites that stimulate or inhibit the MLF cannot always explain the phenotypic distinction. In this work, a multidisciplinary workflow combining non-targeted me…

UPLC-Q-TOF-MSWineBactérie lactiqueApprentissage automatique[SDV.IDA] Life Sciences [q-bio]/Food engineeringYeastMicrobial interactionInteraction microbienne[SDV.AEN] Life Sciences [q-bio]/Food and NutritionMachine learningVinLactic acid bacteriaMetabolomicsLevurePeptidesFT-ICR-MSMétabolomique
researchProduct

Langage et Apprentissage en Interaction pour des Assistants Numériques Autonomes - Une Approche Développementale

2021

The rapid development of digital assistants (DA) opens the way to new modes of interaction. Some DA allows users to personalise the way they respond to queries, in particular by teaching them new procedures. This work proposes to use machine learning methods to enrich the linguistic and procedural generalisation capabilities of these systems. The challenge is to reconcile rapid learning skills, necessary for a smooth user experience, with a sufficiently large generalisation capacity. Though this is a natural human ability, it remains out-of-reach for artificial systems and this leads us to approach these issues from the perspective of developmental Artificial Intelligence. This work is thus…

Apprentissage en interaction[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI]Langage naturelApprentissage automatique Machine Learning[SCCO.COMP]Cognitive science/Computer science[INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG][SCCO.LING]Cognitive science/Linguistics[STAT.ML] Statistics [stat]/Machine Learning [stat.ML][INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]Digital assistantsCognition[STAT.ML]Statistics [stat]/Machine Learning [stat.ML][INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]Natural languageInteractive learning[SCCO.COMP] Cognitive science/Computer scienceMachine learning[INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC]Intelligence artificielle développementale[SCCO.LING] Cognitive science/Linguistics[INFO.INFO-HC] Computer Science [cs]/Human-Computer Interaction [cs.HC]developmental artificial intelligenceAssistant Numérique
researchProduct

Configuration optimale des aires de marché et coûts de transport

1991

La théorie des Places Centrales étudiée par LÖSCH (4) et CHRISTALLER (5) a pour objet l'examen et la construction d'un paysage hiérarchisé. Celui-ci est basé sur un système d'aires de marché qui possèdent des configurations précises (hexagonales et carrées principalement). En fait raire de marché correspond à la zone d'influence d'un offreur. LÖSCH (4, p 130) a supposé que la libre entrée de firmes indépendantes localisées sur une plaine où sont situés des demandeurs équidistants entraine une transformation des aires circulaires en aires hexagonales et ainsi une maximisation du nombre de firmes par unité d'aire. HARTWICK (2) examine analytiquement le théorème de LÖSCH concernant les aires d…

Control theoryStatistics[ SHS.ECO ] Humanities and Social Sciences/Economies and finances[SHS.ECO]Humanities and Social Sciences/Economics and Finance[SHS.ECO] Humanities and Social Sciences/Economics and FinanceOperational researchRecherche opérationnelleAutomatique
researchProduct

Appropriateness between physical space and multicentre economic space in localization problems

1991

Location models are constructed in mathematical economic spaces whereas people locate themselves in real or physical spaces. If economic spaces are multicentric ones, their properties are different from physical spaces. We say that these two spaces are not symmetric. Hence, mathematical location model can lead to an optimal location solution which doesn't' exist in physical space. But, if we admit that an optimal location solution owns more or less to a function of demand of location, we can resolve this question. Then, fuzzy demand functions of location are defined in multicentric spaces and an illustration of this concept is presented.

Transport planningControl theoryUrban planningRural planning[SHS.GEO] Humanities and Social Sciences/Geography[SHS.GEO]Humanities and Social Sciences/GeographyOperational researchRecherche opérationnelleCountryside conservationAutomatique[ SHS.GEO ] Humanities and Social Sciences/Geography
researchProduct

The Influence of the feedback control of the hexapod platform of the SAAM dynamic driving simulator on neuromuscular dynamics of the drivers

2012

Multi sensorial cues (visual, auditory, haptic, inertial, vestibular, neuromuscular) [Ang2] play important roles to represent a proper sensation (objectively) and so a perception (subjectively as cognition) in driving simulators. Driving simulator aims at giving the sensation of driving as in a real case. For a similar situation, the driver has to react in the same way as in reality in terms of ‘self motion’. To enable this behavior, the driving simulator must enhance the virtual immersion of the subject in the driving situation. The subject has to perceive the motion of his own body in the virtual scene of the virtual car as he will have in a real car. For that reason, restituting the iner…

[PHYS.MECA.VIBR] Physics [physics]/Mechanics [physics]/Vibrations [physics.class-ph]Base de données [Informatique]Motion cueingModélisation et simulation [Informatique]Mécanique: Vibrations [Sciences de l'ingénieur]optimal controlAutomatique [Informatique]Robotique [Informatique][INFO.INFO-DB] Computer Science [cs]/Databases [cs.DB]EMG analysisdynamic driving simulatorsLQR[INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO]open loop control[MATH.MATH-OC] Mathematics [math]/Optimization and Control [math.OC]Optimisation et contrôle [Mathématique]motion sicknessInterface homme-machine [Informatique][SPI.MECA.VIBR] Engineering Sciences [physics]/Mechanics [physics.med-ph]/Vibrations [physics.class-ph]motion cue[INFO.INFO-MO] Computer Science [cs]/Modeling and Simulation[INFO.INFO-HC] Computer Science [cs]/Human-Computer Interaction [cs.HC][INFO.INFO-AU] Computer Science [cs]/Automatic Control EngineeringMotion cueing motion sickness LQR optimal control EMG analysis dynamic driving simulatorsclosed loop control
researchProduct

Estimation des performances, test et contrôle des systèmes cyber-physiques employant des réseaux de communication non idéaux

2020

Wireless technology is a key enabler of the promises of Industry 4.0 (Smart Manufacturing). As such, wireless technology will be adopted as a principal mode of communication within the factory beginning with the factory enterprise and eventually being adopted for use within the factory workcell. Factory workcell communication has particular requirements on latency, reliability, scale, and security that must first be met by the wireless communication technology used. Wireless is considered a non-ideal form of communication in that when compared to its wired counterparts, it is considered less reliable (lossy) and less secure. These possible impairments lead to delay and loss of data in indus…

Fabrication intelligenteIndustrial wireless testbed[INFO.INFO-TS] Computer Science [cs]/Signal and Image ProcessingSmart manufacturingApprentissage automatiqueSystems modelingGraph databaseBase de données graphe[INFO.INFO-TS]Computer Science [cs]/Signal and Image ProcessingMachine learningIndustrial wirelessModelisation systémeCommunications sans fil industrielBanc d'essai sans fil industriel
researchProduct

Quasi order, pseudo order and not order

1995

This study, after having presented the structure of total semi-order and that of pseudo-order one, presents a new preference structure called non order. This one generalizes both the semi-order structure and the pseudo-order one. The details analysis are based on the usual concepts of the relationnal approach of preference modelling and on some new concepts and principles which fit the imprecise context. These new principles are : imprecise discriminant power, imprecise transitivity, imprecise intransitivity and generalized limited comparability. The new concepts are : preference relationnal constituent and preference relationnal state.

[ MATH ] Mathematics [math]Control theoryStatistics[MATH] Mathematics [math]Operations researchOperational researchRecherche opérationnelleAutomatique
researchProduct

Recursive estimators 2

1991

In this paper the techniques for recursive estimation of linear model are extended to non-spherical disturbances. First we present the recursive formulae of generalized least squares. The recurrence relation for the residual sum of squares are derived. We show in the second part of the paper a recursive formulae of generalized instrumental variables.

[ MATH ] Mathematics [math]Control theoryStatistics[MATH] Mathematics [math]Estimation récursiveOperational researchRecherche opérationnelleAutomatique
researchProduct