Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Vincent Hilaire
  • UTBM
    F-90010 Belfort, FRANCE
  • +33384583009

Vincent Hilaire

UTBM, Ciad, Faculty Member
Nowadays, telemonitoring systems are increasingly used, due to the increasing of life expectancy and chronic diseases. Indeed, chronic diseases and disabilities due to advancing age are responsible for health care costs increasingly... more
Nowadays, telemonitoring systems are increasingly used, due to the increasing of life expectancy and chronic diseases. Indeed, chronic diseases and disabilities due to advancing age are responsible for health care costs increasingly growing. Telemonitoring systems provide a low cost way to monitor patients and their needs in the comfort of their own homes. In first systems, the data were collected then sent directly to physicians to be interpreted. Nowadays, thanks to technological advancements, software and systems have been developed to process data, on a simple computer or even smartphone. In this paper, we present e-Care telemonitoring system that combines the semantic web and expert system. E-Care is based on generic ontologies and a decision support system. The decision support system uses ontologies as knowledge base and an inference engine to detect abnormal situations. E-Care platform has a generic open architecture, which cans include other knowledge coming from other systems. We'll show how to integrate data of auscultation sounds in this architecture.
We will present in this paper how to ensure the creation, the validation and the sharing of ideas by using a Semantic Wiki approach. We describe the system called Wiki-I which is used by engineers to allow them to formalize their ideas... more
We will present in this paper how to ensure the creation, the validation and the sharing of ideas by using a Semantic Wiki approach. We describe the system called Wiki-I which is used by engineers to allow them to formalize their ideas during the research solutions activities. Wiki-I is based on an ontology of the innovation domain which allows to structure the wiki pages and to store the knowledge posted by the engineers. In this paper, we will explain how Wiki-I ensures the reliability of the innovative ideas thanks to an idea of evaluation process. After explaining the interest of the use of semantic wikis in innovation management approach, we describe the architecture of Wiki-I with its semantic functionalities. At the end of the paper, we prove the effectiveness of Wiki-I with an ideas evaluation example in the case of students challenge for innovation.
In the context of globalization, companies need to capitalize on their knowledge. The knowledge of a company is present in two forms tacit and explicit. Explicit knowledge represents all formalized information i.e all documents (pdf,... more
In the context of globalization, companies need to capitalize on their knowledge. The knowledge of a company is present in two forms tacit and explicit. Explicit knowledge represents all formalized information i.e all documents (pdf, words …). Tacit knowledge is present in documents and mind of employees, this kind of knowledge is not formalized, it needs a reasoning process to discover it. In this paper, we propose a novel approach for documents clustering that is based on word clusters automatically extracted from the documents. The word concepts are considered as concepts candidates. In a second step, word clusters are used to ease the automatic building of ontologies from a given corpus. Some experiments allows for a validation of the whole approach. The chosen corpus is Reuters-21578 that is among the most used for text categorization research.
Telemonitoring systems are nowadays being extensively developed and utilized, due to the fact that the worldwide elderly population is increasing. In fact, the use of a telemonitoring system alleviate the problem of health costs by... more
Telemonitoring systems are nowadays being extensively developed and utilized, due to the fact that the worldwide elderly population is increasing. In fact, the use of a telemonitoring system alleviate the problem of health costs by providing a reliable way of alerting the healthcare personnel. The design of a telemonitoring system is a real challenge. In this context, the architecture of a telemonitoring system must be generic and flexible and its knowledge must be well defined so it can be shared between actors of the system. In this paper, we present a methodology for the design of a telemonitoring system. This methodology is based on the use of multi-agent system, ontologies and expert systems. The proposed approach relies on an existing multi-agent methodology known as ASPECS. The latter is adapted to construct a telemonitoring system by adding several activities that introduce ontologies and expert systems. This methodology is applied to E-care, a platform designed for a large scale computing. E-care is a telemonitoring platform for patients suffering from heart failure. As part of this platform, several experiments were conducted to validate this methodology at Strasbourg University Hospital (Strasbourg, France). Preliminary results show that this platform is able to assist health care professionals. E-care processes data sent from the sensors and generates automatically alerts in order to detect early risk situations of heart failure.
Le travail presente dans cette these s'inscrit dans le cadre d'une demarche methodique pour la construction de specifications formelles de systemes multi-agents. L'idee de base est de definir de tels systemes comme un ensemble... more
Le travail presente dans cette these s'inscrit dans le cadre d'une demarche methodique pour la construction de specifications formelles de systemes multi-agents. L'idee de base est de definir de tels systemes comme un ensemble d'entites mettant en oeuvre des comportements generiques, des roles, entre lesquels des interactions sont specifiees. Ces roles et ces interactions sont structures en unites appelees organisations. Pour concevoir les specifications deduites de cette demarche, un langage d'expression d'objets actifs et reactifs est propose. Ce langage est base sur l'utilisation de deux formalismes, object-z et statecharts. La composition de ces formalismes fait l'objet d'une etude et se decompose en un ensemble de regles qui autorise leur integration syntaxique et semantique. Ce langage multi-formalisme est caracterise par : un pouvoir d'expression suffisant pour specifier les differents aspects des sma, des outils pour analyser une specification et la possibilite de raffinements pour aboutir a une specification proche d'une implementation. Notre demarche de specification de systemes multi-agents s'inscrit dans un processus de prototypage et de verification. Le prototypage realise grace a l'animation des statecharts permet de valider la specification par rapport au comportement attendu du systeme. La verification est rendu possible par l'expression de la semantique du langage multi-formalismes avec des systemes de transitions et a l'utilisation de ces systemes de transitions par des logiciels adequats. La specification d'un systeme multi-agents est base sur un framework exprime avec le langage multi-formalisme qui formalise les concepts de role, interaction et organisation. Nous concretisons cette etude par la specification de deux systemes multi-agents sur lesquelles nous mettons en oeuvre le prototypage et la verification.
Document classification is a large body of search, many approaches were proposed for single label and multi-label classification. We focus on the multi-label classification more precisely those methods that transformation multi-label... more
Document classification is a large body of search, many approaches were proposed for single label and multi-label classification. We focus on the multi-label classification more precisely those methods that transformation multi-label classification into single label classification. In this paper, we propose a novel problem transformation that leverage label dependency. We used Reuters-21578 corpus that is among the most used for text categorization and classification research. Results show that our approach improves the document classification at least by 8% regarding one-vs-all classification.
Modeling and design of complex intelligent systems (Intelligent transportation systems, shared health information systems, resource sharing systems, Smart city management systems, etc.) is a very difficult task due to the lack of design... more
Modeling and design of complex intelligent systems (Intelligent transportation systems, shared health information systems, resource sharing systems, Smart city management systems, etc.) is a very difficult task due to the lack of design processes capable of covering all the characteristics of these types of systems: systems that require both a hierarchical structure which allows to bring together different levels of abstraction within the same system and require the maintenance of regulation and social control of the various entities involved in these systems by using a set of norms. Holonic Multiagent System (HMAS) forms a promising approach to software engineering for the modeling and development of hierarchical complex systems. One of the main challenges currently faced in HMAS research is that of social control. In particular, how can the HMAS be configured and organised given their structure of control and regulation? One of the main solutions is to employ the use of norms. Therefore, norms have been proposed as a mechanism for coordinating and controlling of various entities behaviors involved in the system. In this paper, we propose a new model of norms adapted to the holonic structure of HMAS. To do this, (1) we introduce two new types of norms: internal (private) and external (public) norms; (2) we identify and verify the alignment between these two types of norms. These two types of norms have implications for the control, organization and structure of holons.
Increasing collaborative work and distributing information creates a request for large-scale and flexible systems in regulated environments. A promising approach in the field of multi-agent system is the design and development of complex,... more
Increasing collaborative work and distributing information creates a request for large-scale and flexible systems in regulated environments. A promising approach in the field of multi-agent system is the design and development of complex, hierarchical and critical systems. These systems require both a hierarchical structure that allows to make together different levels of abstraction within the same system and require the maintenance of social control of the various entities involved in these systems by using social norms. Several proposals on normative models for multi-agent systems have been made in order to design agent societies in norms-based environments. However, they are not adapted to support holonic systems, i.e. those who allow to model complex organizations involving several levels simultaneously. In this paper, we propose a new metamodel, called NCRIO (Norm, Capacity, Role, Interaction, and Organization), for the design of normative holonic multi-agent systems (NHMAS). This metamodel is an extension of the CRIO (Capacity, Role, Interaction, and Organization) metamodel, which allows the design of holonic multi-agent systems (HMAS). The NCRIO metamodel retains the properties of the HMASs and adds normative concepts (Norms and Contracts) to maintain social control in these systems. This new metamodel allows the design for complex (which require a hierarchical structure) and critical (which require social control) systems.
ABSTRACT
This paper aims to present an approach in order to share knowledge between the business actors of the extended enterprise. This approach is based on a semantic wiki that access the organizational memory of our knowledge management system... more
This paper aims to present an approach in order to share knowledge between the business actors of the extended enterprise. This approach is based on a semantic wiki that access the organizational memory of our knowledge management system OCEAN. This principle allows us, firstly to share knowledge in order to facilitate the individual work, and secondly to reuse capitalized knowledge automatically.
Quantum computing offers a new approach to the problem modeling and solving. This paper deals with the quantum modeling of reactive agents. It also proposes a quantum algorithm to implement the subsumption architecture, widely used by... more
Quantum computing offers a new approach to the problem modeling and solving. This paper deals with the quantum modeling of reactive agents. It also proposes a quantum algorithm to implement the subsumption architecture, widely used by reactive agents, particularly in robotics. This work shows the contribution of the formalism proposed by quantum mechanics to the modeling and the proof of certain properties of the agent behavior. After, the definition of the reactive agent state modeling, the paper suggests a behavior modeling approach based on two steps for subsumption architecture. The first one models the preset behavior that links each action to the perception states. The second one determines, among several actuated actions, the one that the robot must achieve. The subsumption architecture raises the challenge of modeling hierarchical priority of actions. To this end, a multipartite entanglement is used in the second step. More precisely, the paper proposes and generalizes a W-state circuit in order to be used for modeling hierarchical priority actions and controlling the robot accordingly. The result of both steps provides a formal model that links the robot’s perception (input) to the actions (output), with respect to the subsumption architecture. The proposed model of agent is simulated using IBM quantum computer. The simulation shows that the model can either be served as a control unit of the robot (CU) to obtain the suitable action or to simulate the robot behavior.
In this article, we describe a multi agent approach for supporting learning activities in a Virtual Learning Environment context. In order to assist teachers who monitor learning processes, viewed as a specific type of collaboration, the... more
In this article, we describe a multi agent approach for supporting learning activities in a Virtual Learning Environment context. In order to assist teachers who monitor learning processes, viewed as a specific type of collaboration, the proposed system estimates a behavioral (sociological) profile for each student. This estimation is based on automatic analysis of students’ textual asynchronous conversations. The determined profiles are proposed to the teacher and may provide assistance to teacher during tutoring tasks. This paper specifically proposes definitions of the used sociological profiles, and presents the architecture of the Multi-Agent System (MAS) determining the profiles. This MAS relies on a fuzzy logic based strategy for representing the knowledge of the teacher. The system was experimented with students of the master “software quality” of the Ibn Tofail University. The results obtained show that the proposed approach is effective and gives satisfactory results.
In the context of globalization, companies need to capitalize on their knowledge. The knowledge of a company is present in two forms tacit and explicit. Explicit knowledge represents all formalized information i.e all documents (pdf,... more
In the context of globalization, companies need to capitalize on their knowledge. The knowledge of a company is present in two forms tacit and explicit. Explicit knowledge represents all formalized information i.e all documents (pdf, words …). Tacit knowledge is present in documents and mind of employees, this kind of knowledge is not formalized, it needs a reasoning process to discover it. In this paper, we propose a novel approach for documents clustering that is based on word clusters automatically extracted from the documents. The word concepts are considered as concepts candidates. In a second step, word clusters are used to ease the automatic building of ontologies from a given corpus. Some experiments allows for a validation of the whole approach. The chosen corpus is Reuters-21578 that is among the most used for text categorization research.
This paper deals with using an evolutionary algorithm (EA) as a prototyping tool to develop and refine a multi agents system (MAS) for problem solving. In the case of (distributed) solving, MAS may lack some knowledge about the solving... more
This paper deals with using an evolutionary algorithm (EA) as a prototyping tool to develop and refine a multi agents system (MAS) for problem solving. In the case of (distributed) solving, MAS may lack some knowledge about the solving mechanism. Using a GA as a prototyping tool thus enables to extract heuristics for use in the MAS design. This approach, based upon a model conciliating both EA and MAS perspectives, is tested on the antenna parameter setting problem (APSP) from the field of radiomobile networks. We demonstrate the feasibility and interest of such an approach for complex problems. Moreover, we advocate the use of MAS techniques for the field of radiomobile networks.

And 183 more