Cet article traite de style d’apprentissage en tant que critère d’adaptation d’un cours en ligne. Une première étape consiste à choisir le modèle des styles d’apprentissage. La sélection de ces styles est réalisée par un questionnaire dédié. D’autre part, les activités d’apprentissage sont conçues afin de refléter les dimensions liées aux styles d’apprentissage. Enfin, la présentation de ces activités est gérée par un module d’adaptation probabiliste. En nous appuyant sur les méthodes et les techniques proposées pour la modélisation et l’adaptation, nous avons conçu un système hypermédia d’enseignement adaptatif centré sur les styles d’apprentissage. L’approche a été validée expérimentalement et les résultats obtenus sont encourageants.This article discusses learning styles as a criterion of adaptation of a course online. A first step is to choose the model of learning styles. The identification of these styles is performed by a dedicated questionnaire. On the other hand, learning activities are designed to reflect the dimensions related to learning styles. Finally, the presentation of these activities is managed by a probabilistic adaptation module. Based on the methods and techniques proposed for modeling and adaptation, we designed an adaptive hypermedia system that focuses on learning styles. The approach was validated experimentally and the results are encouraging
The deployment of 4G/LTE (Long Term Evolution) mobile network has solved the major challenge of high capacities, to build real broadband mobile Internet. This was possible mainly through very strong physical layer and flexible network architecture. However, the bandwidth hungry services have been developed in unprecedented way, such as virtual reality (VR), augmented reality (AR), etc. Furthermore, mobile networks are facing other new services with extremely demand of higher reliability and almost zero-latency performance, like vehicle communications or Internet-of-Vehicles (IoV). Using new radio interface based on massive MIMO, 5G has overcame some of these challenges. In addition, the adoption of software defend networks (SDN) and network function virtualization (NFV) has added a higher degree of flexibility allowing the operators to support very demanding services from different vertical markets. However, network operators are forced to consider a higher level of intelligence in their networks, in order to deeply and accurately learn the operating environment and users behaviors and needs. It is also important to forecast their evolution to build a pro-actively and efficiently (self-) updatable network. In this chapter, we describe the role of artificial intelligence and machine learning in 5G and beyond, to build cost-effective and adaptable performing next generation mobile network. Some practical use cases of AI/ML in network life cycle are discussed.
In recent years, Flipped Classroom started to be used as an effective way of teaching Engineering among various strategies in higher education. However, enabling and using the flipped learning is a complicated task, not a straightforward goal that can be simply achieved through a combination of face-to-face and online activities. It requires a more sophisticated understanding of effective teaching methods to manage the shift from the traditional to the flipped learning and the optimum adaptation of technology as part of this change. Given this challenge, this research work provides a personalized model of the flipped classroom and investigates through a case study in an Engineering School how our approach can be used to improve teaching of Information and Communication Technology (ICT) Engineering. It assesses by using empirically data related to the interaction of the various actors at different levels of abstraction, particularly from a gender perspective, the relevance and the impact of the flipped classroom on student learning and achievement in ICT Engineering Education.
Dans cet article, nous présentons la mise en oeuvre, l’expérimentation et l’évaluation d’une approche pour la recommandation des chemins d’apprentissage dans un cours en ligne. Le processus de recommandation est inspiré de l’intelligence en essaim et plus particulièrement de l’optimisation par colonies de fourmis (OCF) (ant colony optimization [ACO]). Dans ce contexte, nous avons considéré une différenciation des chemins d’apprentissage en fonction de l’activité explorée pour l’apprentissage d’un cours.Dans l’objectif de recommander des chemins d’apprentissage considérés optimaux et d’évaluer ainsi leur impact sur l’apprentissage d’un cours en ligne, l’approche proposée est basée à la fois sur la recommandation de chemins pertinents par l’enseignant et sur les résultats stockés au fur et à mesure par les apprenants sur les chemins empruntés. Notre approche a été validée expérimentalement et les résultats obtenus ont montré l’émergence d’un chemin d’apprentissage favorisant la réussite d’un nombre d’apprenants relativement considérable.In this article, we present the implementation, the experimentation and the evaluation of an approach for the recommendation of learning paths in an online course. The recommendation process is inspired by swarm intelligence and especially the ant colony optimization (ACO). In this context, we considered a differentiation of the learning paths based on the explored educational activity for learning a lesson.With the aim to recommend learning paths considered optimal and thus assess their impact on the learning of an online course, the proposed approach is based both on the recommendation of relevant paths by the teacher and the result stored progressively by learners on the paths taken. Our approach was validated experimentally and the results showed the emergence of a learning path promoting the success of a relatively considerable number of learners
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.