A5046356004- Online Learning and Analytics
- Intelligent Tutoring Systems and Adaptive Learning
- Online and Blended Learning
- Image Retrieval and Classification Techniques
- Recommender Systems and Techniques
- Learning Styles and Cognitive Differences
- Innovative Teaching and Learning Methods
- Open Education and E-Learning
- Advanced Graph Neural Networks
- Brain Tumor Detection and Classification
- Elasticity and Material Modeling
- Computer Graphics and Visualization Techniques
- Topic Modeling
- 3D Shape Modeling and Analysis
- Advanced Mathematical Modeling in Engineering
- Geological and Geophysical Studies Worldwide
- Medical Image Segmentation Techniques
- Advanced Image and Video Retrieval Techniques
- Data Management and Algorithms
- Semantic Web and Ontologies
- Advanced Neural Network Applications
- Educational Technology and Assessment
- Neural Networks and Applications
- Complex Systems and Time Series Analysis
- Mineral Processing and Grinding
Cadi Ayyad University
2011-2024
Sorbonne Université
1997
Personalized e-learning implementation is recognized one of the most interesting research areas in distance web-based education.Since learning style each learner different we must to fit elearning needs learners.This paper discusses teaching strategies matching with learner's personality using Myers-Briggs Type Indicator (MBTI) tools.Based on an innovative approach, a framework for building adaptive management system by considering preference has been developed.The profile initialized...
In this article, we present a novel approach for creating semantic groups of learners in an educational platform using Graph Neural Networks (GNN) and GraphSAGE. The increasing availability data necessitates advanced methodologies to enhance personalized learning experiences. Traditional techniques often fall short capturing the complex relationships inherent such data. To address this, leverage GraphSAGE, inductive framework, generate meaningful embeddings that represent diverse attributes...
Personalized courseware authoring based on recommender system, which is the process of automatic learning objects selecting and sequencing, recognized as one most interesting research field in intelligent web-based education. Since learner’s profile each learner different from to another, we must fit needs learners. In fact knowledge profile, it easier recommend a suitable set enhance process. this paper describe new adaptive system-LearnFitII, can automatically adapt dynamic preferences...
Personality and individual differences are effective parameters in human activities such as learning. Since the learning style of each learner is different, we must fit to different needs learners. In this paper, an innovative approach proposed by considering learner's preferences. Using Myers-Briggs Type Indicator's (MBTI) tools, a framework for adaptive teaching strategies has been developed e-learning context. Moreover, experiment was conducted evaluate performance our approach. The...
E-learning is increasingly gaining popularity in organizational and institutional learning for its several benefits to learn anywhere, anytime, anyplace. Therefore, explosive growth of has caused difficulty locating appropriate activities learner this context, it becomes relatively widespread method learner. Several research e-learning mainly focused on improving achievements based recommendation technique. An ideal recommender system environment should be built with both accurate goals. To...
The use of graphs as a method storing data has begun to rise significantly in recent years, due the new way representing graphs. This is leveraged by structure that facilitate modeling interactions between real-world entities. With rapid development technologies such machine learning and deep learning, digitalization education entered era with artificial intelligence main feature. As an important part technology, knowledge graph format provides possibilities for smart promotes innovation...
Abstract In this paper, a novel method for binary image comparison is presented. We suppose that the set of transactions and items. The proposed applies along rows columns an image; represented by all frequent itemset. Firstly, are considered as Secondly, we items transactions. Besides, also apply our technique to color firstly segment each segmented region image. tested on MPEG7 database compared with moment’s show its efficiency.
In this work, a new method is presented for the representation of 3D objects with binary matrix. This based on two stages: normalization and quantization. allows us to compare by computing similarity between them. fact our algorithm compute matrix, frequency matrix cluster coordinates. So we can identify an object comparing those representations.
In this work we discuss the problems of template matching and propose some solutions. Those are: 1) Template image search differ by a scale, 2) or is object rotation, 3) an affinity. The well known method NCC (Normalized Cross Correlation); can not handle affinity occlusion. Also preferred for binary image. So here to use index similarity example Jaccard index.
The COVID-19 <span>pandemic is increasingly gaining popularity when discussing e-learning in the context of institutional and organizational learning because its numerous benefits which make it possible for learners to learn regardless circumstances and/or timing. Therefore, expanding dominion online has caused problem terms determining adequate activities learner this context, relatively becomes a widely used technique learners. Several studies focused mainly on increasing student...
In this work, we propose to compare affine shape using Hausdorff distance (HD), Dynamic Time Warping (DTW), Frechet (DF), and Earth Mover (EMD). Where there is only a change in resolution are computed between coordinates because the not invariant under rotation or affinity. case of transformation, distances calculated but Arc length Affine length. while The main advantage invariance resolution, rotation,