Papers by Catherine Garbay
This paper deals with monitoring the health status of a patient at home so as to detect critical ... more This paper deals with monitoring the health status of a patient at home so as to detect critical evolutions over a scale of several days or weeks. A multivariate simulation is used as a way to overcome the lack of experimental data required for studying this decision-making issue. The simulation process needs to be driven in a rigorous and robust way. Due to that, and to deal with heterogeneity and complexity, we make use of an hybrid and refinement methodology. It involves the fusion of several types of models and knowledge, as well as the implementation of a cascade structure for the simulation process.
2015 23rd European Signal Processing Conference (EUSIPCO), 2015
Data Revues 16310691 03250004 02014348, Mar 23, 2008
In this paper, we present a multi-agent framework for data mining in electromyography. This appli... more In this paper, we present a multi-agent framework for data mining in electromyography. This application, based on a web interface, provides a set of functionalities allowing to manipulate 1000 medical cases and more than 25000 neurological tests stored in a medical database. The aim is to extract medical information using data mining algorithms and to supply a knowledge base with pertinent information. The multi-agent platform gives the possibility to distribute the data management process between several autonomous entities. This framework provides a parallel and flexible data manipulation. To cite this article: J. Balter et al., C. R. Biologies 325 (2002) 375-382.
Lecture Notes in Computer Science, 2015
In image processing, the segmentation is a very important step, mainly because of its influence o... more In image processing, the segmentation is a very important step, mainly because of its influence on the feature evaluation. During the segmentation process, problems occur either due to possible ambiguities in the pixel labelling or due to frequent contacts between different components. This paper describes an iterative method, designed to segment convex poorly contrasted or touching objects which is based on the association of two notions, one related to the object colour and the other to its shape, in terms of convexity. Starting from an initial connected set of points, pixels are iteratively aggregated to that set using a colour distance. The processing stops when convexity of the iterated set is reached. Application to a particular class of convex objects, such as blood and bone marrow cells is presented.
Lecture Notes in Computer Science, 2015
La construction automatique de scénariosà partir des signaux (séries temporelles) produits par le... more La construction automatique de scénariosà partir des signaux (séries temporelles) produits par les appareils de surveillance de patients en anesthésie réanimation est le premier pas vers l'élaboration de systèmes de monitoring intelligent. Mais dans ce contexte, les connaissances a priori ne sont pas suffisantes pour orienter efficacement un apprentissageà partir des données complexes que sont les séries temporelles. Nous proposons donc une approche hors ligne non supervisée et limitant l'introduction de biais afin de faireémerger des scénarios. Nous définissons pour cela le cadre d'un système multi-agents (SMA) s'appuyant sur une forte interaction entre une phase de traduction dynamique des séries numériques en séries symboliques temporelles et une phase d'apprentissageà partir de ces séries.
IEEE Transactions on Biomedical Engineering, 1999
Proceedings of the 8th Conference on Ai in Medicine in Europe Artificial Intelligence Medicine, 2001
ABSTRACT A multi-agent framework for data mining in EMG is presented. This application based on a... more ABSTRACT A multi-agent framework for data mining in EMG is presented. This application based on a Web interface provides a set of functionnalities allowing to manipulate one thousand medical cases and more than twenty five thousands neurological tests stored in a medical database. The aim is to extract medical informations using data mining algorithms and to supply a knowledge base with pertinent information. The multi-agent platform gives the possibility to distribute the data management process between several autonomous entities. This framework provides a parallel and flexible data manipulation.
* Available as a photocopy reprint only. Allow two weeks reprinting time plus standard delivery t... more * Available as a photocopy reprint only. Allow two weeks reprinting time plus standard delivery time. No discounts or returns apply. ... Standard delivery in the US is 7 to 10 business days and outside the US delivery is 4 to 6 weeks or longer. For further details, please see shipping policy. ... Click the paper title to view an abstract or to order an individual paper. ... The main objective of this paper is to describe how Dempster-Shafer's (DS) theory of belief functions fits in the framework of valuation-based systems (VBS). Since VBS serves as a framework for ...
2004 12th European Signal Processing Conference, Sep 1, 2004
Defining the similarity of objects is crucial in any data analysis and decision-making process. F... more Defining the similarity of objects is crucial in any data analysis and decision-making process. For those which effectively deal with moving objects, the main issue becomes the comparison of trajectories, also referred to as time-series. Moreover, complex applications may require an object to be a multidimensional vector of heterogeneous parameters. In that paper, we propose a similarity measure for heterogeneous multivariate time-series using a non-metric distance based on the Longest Common Subsequence (LCSS). The proposed definition allows for imprecise matches, outliers, stretching and global translating of the sequences in time. We demonstrate the relevance of our approach in the context of identifying similar behaviors of a person at home.
Pattern Recognition Letters, Aug 1, 1997
ABSTRACT
Ts Traitement Du Signal, 1995
We work on the design of computerized systems that support experts during their complex and poorl... more We work on the design of computerized systems that support experts during their complex and poorly formalized data interpretation process. We consider interpretation as the process by which high level abstracted information is attached to data. We assume that a computer could efficiently helps an expert in such a process via a structural coupling based on their interactions. Enaction appears as a stimulating source of inspiration for the design of such systems. Our approach is applied to the exploration of physiological time series acquired from patients in intensive care unit (ICU).
Catégorie : chercheur/industriel RÉSUMÉ. Le volume de documents disponible sur l'Internet rend di... more Catégorie : chercheur/industriel RÉSUMÉ. Le volume de documents disponible sur l'Internet rend difficile les tâches de recherche d'informations. Parallèlement, des efforts vers la personnalisation de l'Internet permettent l'adaptation des pages web à l'utilisateur. Pour ce faire, les travaux s'orientent vers les concepts des systèmes d'informations adaptatifs et de la génération de résumés de collections de pages. La plupart de ces systèmes cherchent à rendre compte d'une diversité par un synthèse ou à rendre compte d'une cohérence narrative par une organisation spatiale. Nous nous proposons quant à nous d'extraire une collection représentative constituant une cohérence thématique selon des vues logiques afin de générer un document synthétique qui pourra servir de support à une fouille de données. Le système envisagé sera dans un premier temps consacré au domaine médical et en particulier à la génération de documents autour de la technologie des Tissue Microarrays.
Uploads
Papers by Catherine Garbay