Search

In the case of a radiological emergency situation, involving accidental human exposure, it is necessary to establish as soon as possible a dosimetry evaluation. In most cases, this evaluation is based on numerical representations and models of the victims. Unfortunately, personalised and realistic human representations are often unavailable for the exposed subjects. Hence, existing models like the 'Reference Man' representative of the average male individual are used. However, the accuracy of the treatment depends on the similarity of the phantom to the victim. The EquiVox platform (Research of Equivalent Voxel phantom) developed in this work uses the case-based reasoning principles to retrieve, from a set of existing phantoms, the most adapted one to represent the victim. This paper introduces the EquiVox platform and gives the example of in vivo lung monitoring optimisation to prove its efficiency in choosing the right model. It also presents the artificial neural network tools being developed to adapt the model to the victim.

International audience; Platforms expand maintenance systems from centralized systems into e-maintenance platforms integrating various cooperative distributed systems and maintenance applications. This phenomenon allowed an evolution in services offered to maintenance actors by integrating more intelligent applications, providing decision support and facilitating the access to needed data. To manage this evolution, e-maintenance platforms must respond to a great challenge which is ensuring an interoperable communication between its integrated systems. By combining different techniques used in previous works, we propose in this work a semantic mediator system ensuring a high level of interoperability between systems in the maintenance platform.

International audience; Maintenance is becoming more and more crucial in Asset Lifecycle Management information models. Issues such as collecting, handling and using the asset data produced during its lifecycle in a lean and efficient manner are on top of today's research. Customer satisfaction, compliance with environmental friendly legislation, product quality, high performance and reliability are only a few of the benefits improved maintenance methods and tools may provide to enterprises. In this work we combine the benefits of two previous developed models and we develop a model for Semantic Maintenance. The first model we are based on is the PROMISE semantic object model which was made for supporting Closed-Loop Product Lifecycle Management. The second model is the semantic model of e-maintenance developed in PROTEUS project. The new model described in this paper is named “SMAC-Model”. Its aim is to provide advanced maintenance services as well as feedback for the Beginning of Life and input for End of Life. The model is generic and may be used in various Asset Lifecycle Management cases. It is developed to facilitate complex physical assets and to work in industrial environment.

International audience; In case of accidental exposure to radiation, it is necessary to establish as soon as possible a dosimetry report for each victim. In most cases, this report is based on medical images of the victim, enabling the construction of a personalized realistic numerical model, also called a voxel phantom. Unfortunately it is not always possible to perform the medical imaging of the victim since the technology may be unavailable or to avoid additional exposure to radiation. In such cases, the commonly used method is to represent the victim with a numerical model like the "Reference Man", a voxelized phantom representative of the average male individual. The treatment accuracy depends on the diagnosis precision and, consequently, on the similarity of the phantom and/to the victim. A precise dosimetry evaluation requires a personalised and realistic phantom whose biometric characteristics match the victim; such model is often unavailable. The Case-Based Reasoning (CBR) is a problem solving method for the conception of intelligent systems. It imitates the analysis, understanding and reconstruction of the human intelligence. The ReEPh project (Research of Equivalent Phantom) proposes to use the CBR principles to retrieve from a set of phantoms, the most adapted one to the irradiated victim. For this study, the ReEPh platform retrieves, stores and compares existing phantoms to a victim. A graphic interface enables the user to compare victim's characteristics to the ones of the most similar phantoms available in the database. This defines a similarity index presenting the equivalence between the victim and the suggested phantom. Moreover, a confidence index is also assessed to define the uncertainty implied by the RaPC choice procedure. © EDP Sciences, 2010.

International audience; The objective of this paper is to address the diagnosis knowledge-oriented system in terms of artificial intelligence, particular by the Case-Based Reasoning (CBR) approach. Indeed, the use of CBR, which is an approach to problem solving and learning, in diagnosis goes back to a long time with the appearance of diagnostic support systems based on CBR. A diagnostic system by CBR implements an expertise-base composed of past experiences through which the origins of failure and the maintenance strategy are given according to a description of a specific situation of diagnostic. A study is made on the different diagnostic systems based on CBR. This study showed that there was no common methodology for building a CBR system. This design depends primarily on the case representation and knowledge models of the domain application. Consequently, this paper proposes a general design approach of a diagnostic system based on the CBR approach.

International audience; Technological and software progress with the evolution of processes within company have highlighted the need to evolve systems of maintenance process from autonomous systems to cooperative and sharing information system based on software platform. However, this need gives rise to various maintenance platforms. The first part of this study investigates the different types of existing industrial platforms and characterizes them compared to two criteria namely : information exchange and relationship intensity. This allowed identifying the e-maintenance architecture as the current most efficient architecture. despite its effectiveness, this latter can only guarantee technical interoperability between various components. Therefore, the second part of this study proposes a semantic-knowledge based architecture, thereby ensuring a higher level of semantic interoperability. To this end, specific maintenance ontology has been developed.

International audience; We have developed a diagnostic help system dedicated to the maintenance of a supervised industrial system for pallets Transfer (SISTRE). This diagnostic help system is based on a Case-Based Reasoning approach (CBR). The expertise considered in this help system and formalized in the case form in a case-base must be updated, while taking account of its quality. In this objective we propose a method allowing on one hand to structure the case-base and on the other hand to auto-increment it. An experimental study is undertaken through references benchmarks as well as an application on SISTRE.

International audience; In the domain of radiation protection it is not always possible to perform an additional examination such as scanners or Magnetic Resonance Imaging (MRI) for a patient who has been accidentally radiated. However a medical diagnostic must be made as soon as possible to calculate the dosimetric balance. Currently this incidental calculation is based on the available voxelised phantoms which are 3D numerical reconstructions of the human body with the internal organs. The Case-Based Reasoning (CBR) is seen on the one hand like a problem solving method and on the other hand like a technology for the conception of intelligent systems. The ReEPh project (Research of Equivalent Phantom) strikes a new path in the field of problem solving methods in the radiation protection and uses the approach of the CBR to retrieve the set of the phantoms the most adapted to the irradiated victim. For this first version of ReEPh, the retrieval phase uses a Knn Algorithm (K nearest neighbours). We propose a measure of similarity and a confidence index to take into account the uncertainty implied by the possible missing characteristics of the victim. We have developed a graphic interface to view the cases retrieval, and to visually illustrate the combination of measures of similarity and confidence index.

Face à la mondialisation des marchés et à l'arrivée des pays émergents au faible coût de main-d'oeuvre, les entreprises cherchent de plus en plus à réutiliser l'expérience acquise au cours des activités antérieures dans le but d'améliorer les performances de leurs processus industriels : de la conception de produits à la fabrication en passant par la maintenance ou la maîtrise des procédés. Il s'agit d'éviter les erreurs du passé et de reconduire des solutions éprouvées : c'est le retour d'expérience.

International audience; Conditions complexity of management workshop of production manufacturing increases and requires heuristic algorithm adapted to the context. The principal difficulty then lies in the choice of heuristic algorithm to apply. We propose a help method to schedule, and more specifically a parameter setting up's help of an industrial scheduling software, being based on machine learning system able to extract knowledge from data. An inductive learning based on examples system is developed and replaced in a process of ECD (Extraction of Knowledge starting from Data). The first step pf this process is specific to our problem and uses in this case the capacities of simulation of a market software of scheduling.

National audience; La phase d'élaboration du raisonnement à partir de cas a pour objectif de préparer la remémoration en enrichissant la description du problème tel qu'il est saisi par l'utilisateur, afin d'obtenir le problème cible. Cet article tente une première formalisation de l'élaboration en s'appuyant sur un exemple et sous l'hypothèse, assez générale, selon laquelle les problèmes et solutions peuvent être considérés comme des ensembles (ou conjonctions) de descripteurs. Cette formalisation est une définition qui caractérise une fonction d'élaboration. Plusieurs fonctions d'élaboration sont possibles, de celle qui consiste à ne rien faire (le problème cible est le problème saisi par l'utilisateur) à celle qui consiste à ajouter tous les descripteurs déductibles du problème saisi et de la théorie du domaine. Un cas intermédiaire intéressant consiste à ne rajouter au problème saisi par l'utilisateur que les descripteurs susceptibles de jouer un rôle dans le raisonnement, i.e., ceux qui sont liés à des dépendances entre problèmes et solutions.