Search

International audience; In job-shop manufacturing systems, an efficient production schedule acts to reduce unnecessary costs and better manage resources. For the same purposes, modern manufacturing cells, in compliance with industry 4.0 concepts, use material handling systems in order to allow more control on the transport tasks. In this paper, a job-shop scheduling problem in vehicle based manufacturing facility that is mainly related to job assignment to resources is addressed. The considered job-shop production cell has two types of resources: processing resources that accomplish fabrication tasks for specific products, and transporting resources that assure parts’ transport to the processing area. A Variable Neighborhood Search algorithm is used to schedule product manufacturing and handling tasks in the aim to minimize the maximum completion time of a job set and an improved lower bound with new calculation method is presented. Experimental tests are conducted to evaluate the efficiency of the proposed approach.

Over the last decade, the Vehicular Cloud Computing has appeared as an attractive and very promising field of researches. Indeed, with the proliferation of the automotive industry, vehicles have become increasingly equipped with various resources and devices for calculation, communication, storage and detection. These equipments are continually improving even for vehicles intended for everyday use. Less recent than the Vehicular Cloud Computing, the Body Area Networks have emerged as a sub-category of Wireless Sensor Networks technology. These networks are particularly interesting in the medical field. Indeed, it provides a continuous health monitoring of a patient without any constraint on his/her normal daily life activities. Although difficult to highlight in an accident, malaise behind the wheel remains one of the most important causes of traffic accidents. Indeed, it is an increasingly frequent phenomenon that is materialized by a crisis, syncope or a falling asleep. By using Vehicular Cloud Computing and Body Area Networks, we propose, in this work, to undertake persons taken malaise behind the wheel and manage their vehicles in case of loss control. To do this, we will present a new service of Vehicular Cloud Computing called HAaaS "Health-Assistance as a Service". This service provides a decision support able, on the one hand, to monitor and manage the malaise of a driver and, on the other hand, to provide a mechanism for cooperation between vehicles to rescue the driver taken malaise. Our objective is to reduce the number of traffic accidents, the material and human damage that can be caused as well as the time and fuel lost in traffic jams caused by these accidents., Au cours de la dernière décennie, le Cloud Computing Véhiculaire est apparu comme un domaine de recherche attractif et très prometteur. En effet, avec la prolifération de l’industrie automobile, les véhicules sont devenus de plusen plus équipés avec divers ressources et dispositifs de calcul, de communication, de stockage et de détection. Ces équipements sont en continuelle amélioration même pour les véhicules destinés à un simple usage quotidien.Moins récents que le Cloud Computing Véhiculaire, les réseaux de capteurs corporels sont apparus comme une sous-catégorie de la technologie des réseaux de capteurs sans fil. Ces réseaux sont particulièrement intéressants dans le domaine médical. En effet, ils permettent de fournir un suivi et une surveillance continus de la santé d’un patient sans aucune contrainte sur ses activités quotidiennes normales.Bien qu’il soit difficile à mettre en évidence, dans un accident, le malaise au volant reste considéré comme l’une des causes principales d’accidents de la circulation. En effet, c’est un phénomène de plus en plus fréquent qui se matérialise par une crise, une syncope ou un endormissement.En utilisant le Cloud Computing Véhiculaire et les réseaux de capteurs corporels, nous proposons, dans ce travail, de prendre en charge les personnes victimes de malaise au volant et de gérer leurs véhicules en cas de perte de contrôle. Pour ce faire, nous présenterons un nouveau service de Cloud Computing Véhiculaire appelé HAaaS « Health-Assistance as a Service ». Ce service fournit un support d’aide à la décision et de prise en charge capable, d’une part, de surveiller et de gérer le malaise d’un conducteur et, d’autre part, de fournir un mécanisme de coopération entre les véhicules permettant de secourir le conducteur en malaise. Notre objectif est de réduire le nombre d’accidents de la circulation, les dégâts matériels et humains pouvant être engendrés ainsi que le temps et le carburant perdus dans les embouteillages causés par ces accidents.

International audience

The present work fits into the context of recommender systems for educational resources, especially systems that use social information. Based on the research results in the field of recommender systems, social networks and technology-enhanced learning, we defined an educational resource recommendation approach. We rely on social relations between learners to improve recommendation accuracy. Our proposal is based on formal models that generate three types of recommendation, namely recommendation of popular resources, useful resources and recently viewed resources. We developed a learning platform which integrates our recommendation models. In this paper, we present the results of an experiment conducted during six months in a real educational context. The goal of this experiment is to measure the relevance, quality and utility of the recommended resources. We also conduct an offline analysis by using a dataset in order to compare our approach with four baseline algorithms.

International audience

International audience; In this paper we focus on the Job Shop Scheduling Problem (JSSP) using Priority Dispatching Rules. Simulation model for makespan optimization is proposed using different Dispatching Rules (DR) for each machine in the shop floor. Collected results are used for learning base construction. This database will be used to develop an inference model able to select the best DR for every new scheduling problem. This preliminary study shows advantages of using different DR and also saving progress JSSP data

National audience; Nowadays, emergency departments are confronted to exceptional events such as epidemics problems or health crises. These situations increase the patient flow. The consequence of this influx of patients has resulted in problems of ED overcrowding which often increases the length of stay of patients (LOS) in EDs and leads to strain situations. To cope with such situations, ED managers must predict the LOS. In this paper, we propose a model for predicting the patient length of stay (LOS) in ED using data mining techniques. The used data was collected from the pediatric emergency department (PED) in Lille regional hospital centre, France. Our target is to illustrate with a real world case study, how data mining can be benefit to predict LOS and which its limitations.

International audience; In real-world scheduling problems, several kinds of hard-to-predict risk must be considered. Scheduling under uncertainty allows these kinds of risks to be taken into account. This paper provides an overview of the state of the art in scheduling under uncertainty, including a survey on modeling techniques of uncertainty and a survey of the existing positioning typologies and contributions. A new classification scheme for the different approaches to scheduling under uncertainty is proposed and discussed. Several areas for future research are suggested.

International audience; In reactive manufacturing control, the allocation of resources for tasks is achieved in real time. When a resource becomes available it chooses one of the tasks in its queue. This choice is made according to priority rules which are designed to optimize costs, time, etc. In this paper, the aim is to exploit a Job Shop scheduling log and simulations in order to extract knowledge enabling one to create rules for the selection of priority rules. These rules are implemented in a CASI cellular automaton. Firstly, symbolic modelling of the scheduling process is exploited to generate a decision tree from the log and simulations. Secondly, decision rules are extracted to select priority rules for execution in a specific situation. Finally, the rules are integrated in CASI which implements the decisional module of agents in a distributed manufacturing control system.

International audience; This paper focuses on Multi-Agent Systems (MAS) applied to supply chain management (SCM) in the agri-food industry. The supply chain (SC) analysed includes the suppliers, manufacturers and distribution centres, considering that orders are sent by clients to the distribution centres. Many original constraints, such as the capacity of the suppliers and the manufacturers as well as balancing stocks, are supported in our contribution. Our proposal also considers some practical issues in agri-food SCM, such as expiry dates. The aim of our method is to find a near-optimal solution that minimizes costs and time throughout the SC process, whilst favouring reactivity. An AUML model shows the functioning of the MAS in the SC. The results obtained regarding duration and costs related to the execution of client orders were compared with those obtained using a heuristic that solves the optimization problem in the dynamic case, and a mathematical model in the static case.

International audience; The adaptive hypermedia systems or adaptive web applications is a research area between hypermedia and user modeling. It can customize hyperspace to different users. The existing reference models are generic and are not dedicated to educational systems. This chapter presents in the first part, a reference model that is specific to adaptive educational hypermedia systems. This model is called ALEM (Adaptive Learning Environment Model). It consists of a domain model, a learner model, a course structuring model and an adaptation model. The main contribution of this model is modeling the adaptive learning curriculum. Furthermore, we develop the UML Tutor application which is an educational adaptive hypermedia system based on our reference model.

International audience; The work presented in this paper is a contribution to solving a widespread problem in the field of system design, embedded the placement of a large application on an architecture (NOC). Application is represented by a set of tasks that communicate with each other by sending message via bus on a heterogeneous architecture. Our role is to place the tiles (task) on different elements (core) of architecture with the objectives of minimizing time execution and the energy consumption under the constraints of load balancing, bandwidth, available memory and size of the queue waiting processors. To solve this problem, we used in the context of our present work, a new meta-heuristic algorithm Particle Swarm. it has proved its effectiveness in many fields such as optimization of networks, image processing and even control of industrial systems but it was never applied in our domain.

International audience; Les systèmes hypermédias adaptatifs (SHA) ou les applications Web adaptatifs sont un axe de recherche entre les hypermédias et la modélisation de l’utilisateur. Les SHA permettent de personnaliser l’hyperespace aux différents utilisateurs. Les modèles de référence existants sont génériques et ne sont pas dédiés aux systèmes éducatifs. Cet article présente un modèle de référence qui est spécifique aux systèmes hypermédias adaptatifs éducatifs. Ce modèle est baptisé ALEM (Adaptive Learning Environment Model). Il est composé d’un modèle de domaine, d’un modèle d’apprenant, d’un modèle de structuration de cours et d’un modèle d’adaptation. L’apport principal de ce modèle est la modélisation du parcours personnalisé de l’apprenant.