A5052922037- Online Learning and Analytics
- EEG and Brain-Computer Interfaces
- Geological and Geophysical Studies Worldwide
- Blind Source Separation Techniques
- Anomaly Detection Techniques and Applications
- earthquake and tectonic studies
- AI in cancer detection
- Intelligent Tutoring Systems and Adaptive Learning
- Educational Technology and Assessment
- Human Pose and Action Recognition
- Face and Expression Recognition
- Error Correcting Code Techniques
- Advanced Neural Network Applications
- Advanced Wireless Communication Techniques
- Innovative Teaching and Learning Methods
- Emotion and Mood Recognition
- Sentiment Analysis and Opinion Mining
- E-Learning and Knowledge Management
- Seismology and Earthquake Studies
- Advanced Image and Video Retrieval Techniques
- Seismic Waves and Analysis
- Advanced Computing and Algorithms
- Advanced Adaptive Filtering Techniques
- Infrared Thermography in Medicine
- Archaeological and Historical Studies
Mohammed V University
2012-2023
P300 is one of the most studied and used event related potentials (ERP) in brain computer interfaces (BCI). The classical oddball paradigm usually to evoke from Electroencephalogram (EEG) signals. However, EEG raw data are noisy which make detection very difficult. In this paper, we aim detect wave as accurate possible using appropriate feature extraction method combined with powerful classifier. We compared four methods: Kernel principal component analysis (KPCA), Principal (PCA),...
Online learning has been growing continuously in the last decade, accelerated by pandemic Coronavirus, order to offer learners new possibilities for and guarantee pedagogical continuity. But some aspects, including assessment, are still development require profound changes meet demands of 21st century. However, taking advantage artificial intelligence techniques theories, it would be possible create an assessment system accordance with active approach. This paper illustrates models,...
Nowadays deep learning is considered as a trendy technique in the computer vision domain. It becomes pioneer its main tasks object classification, localization, and detection. Therefore it gave amazing results records. In this paper, we propose new approach to identify localize objects, simultaneously, given scene using Convolutional Neural Networks (CNNs). We an end-to-end for detection pose estimation by formulating bounding boxes containing targeted their pose. Our method based on two...
In recent years, most e-learning platforms include tools that adapt learning materials to learners in order offer them personalized content. Researchers around the world have worked on this topic find solutions help teachers create pedagogical content and object are tailored each learner's skills, abilities, preferences. The purpose of study is review literature works publications adaptive E-learning platforms. More specifically, we dealt with a set questions relating adapted object,...
<span>In this work we implemented STA/LTA trigger algorithm, which is widely used in seismic detection, using Hadoop MapReduce. This<br />implementation allows to find out how effective it type of tasks as well accelerate the detection process by reducing processing time. We tested our implementation on a seismological dataset 14 broadband stations and compare with traditional one. The results show that MapReduce decreased time 34% compared implementation.</span>
3D object recognition and categorization are an important problem in computer vision field. Indeed, this is an area that allows many applications diverse real problems as robotics, aerospace, automotive industry and food industry. Our contribution focuses on using the Deep Belief Networks method (DBN). We extract descriptors from cloud keypoints, then we train resulting vectors with DBN. evaluate performance of two datasets, Washington RGB-D object dataset our own dataset. The...
In this paper, we propose learners course recommender system of the E-Dirassa platform. This system, which distinguishes between new and active learners, adopts three complementary recommendation approaches: content-based as well course-based collaborative filtering for static profile-based learners. Let us also note use multi-criteria decision aid (MDA) techniques choice textual similarity measure to be used in first approach recommendation.
Learning platforms provide new learning opportunities. They are rich on techno-pedagogical tools, enabling learners to collaborate, interact and share resources easily freely between them, based their needs preferences. But the limit of these is that they do not take into consideration learners' motivation. Detecting understanding learner motivational state requires a rigorous analysis interaction traces his environment. This paper aims propose verify some indicators facilitate digital...
Cervical cancer will cause 460 000 deaths per year by 2040, approximately 90% are Sub-Saharan African women. A constantly increasing incidence in Africa making cervical a priority the World Health Organization (WHO) terms of screening, diagnosis, and treatment. Conventionally, diagnosis relies primarily on histopathological assessment, deeply error-prone procedure requiring intelligent computer-aided systems as low-cost patient safety mechanisms but lack labeled data digital pathology limits...
Breast cancer remains one of the deadliest diseases among women. Microcalcifications can be an early indicator a breast cancer. Thus when they are present their detection during screening test is very crucial. But due to small size and low contrast in mammographies difficult. Therefore many computer aided diagnosis mathods have been developped help assist rediologist tests. This paper presents novel approach detect microcalcifications on digitized mammaographies using fuzzy logic support...
Over the last decade, a gradual shift has been observed towards using sentiment analysis approaches to improve online learning environment. In fact, can provide us with valuable information about socio-affective engagement of learners, which is considered key condition for competences development. Lexical, machine learning, and hybrid have become popular choices in research applications. The current study examines classification accuracy learners' based on their interaction messages five...
Over 5% of the world's population (466 million people) has disabling hearing loss. 4 are children. They can be hard or deaf. Deaf people mostly have profound Which implies very little no hearing. world, deaf often communicate using a sign language with gestures both hands and facial expressions. The is full-fledged natural its own grammar lexicon. Therefore, there need for translation models from to languages. In this work, we interested in Modern Standard Arabic(MSAr) into language. We...