Research Reports

Permanent URI for this collectionhttp://dl.cerist.dz/handle/CERIST/34

Browse

Search Results

Now showing 1 - 10 of 21

Applied Gaming-Based Emotion- Driven on Disaster Resilience Training
(CERIST, 2024-11) Hadjar, Hayette; Hemmje, Matthias; Hadjadj, Zineb; Meziane, Abdelkrim
Managing stress in disaster response environments is a critical challenge that requires effective strategies to enhance the resilience and well-being of emergency responders. This study introduces DisasterPlay, a prototype web-based platform designed for resilience training. The prototype features a comprehensive model design, user interface, and implementation using WebXR, facial emotion monitoring, and contactless vital signs monitoring. This approach not only improves the training experience but also aids decisionmakers in selecting the most suitable candidates for high-stakes tasks, thereby enhancing resource allocation. Accessible via web browsers and utilizing cloud-based data processing, this innovative platform aims to provide a robust solution for advancing disaster response strategies.
Toward an Approach for Job Recommender System: Leveraging Hybrid Techniques
(CERIST, 2024-11) Khider, Hadjer; Meziane, Abdelkrim; Hammoudi, Slimane
The rapid evolution of the job market, driven by digitalization and changing business environment dynamics, requires the development of sufficient job recommender systems. A significant number of challenges are facing those job seekers on LinkedIn professional social network. These LinkedIn users are seeking job-maker proposals that align with their business needs. Supporting these job seekers is a real challenge. In order to address this deficiency, we propose a methodology for job recommender systems on the professional social network LinkedIn, based on the user profiles on that platform. This paper presents a user-centric design approach and recommendation process for jobs based on the social profile of the LinkedIn users. The proposed approach to job recommendation combines hybrid techniques, integrating collaborative filtering, content-based filtering, context aware recommendation. In this paper, we introduce a user-centric and interactive framework that enables job seekers to interact with our Job Recommender System to provide the most relevant and valuable recommendations. The proposed framework is designed to addressing common challenges in the field; this approach aims to enhance recommendation accuracy and user satisfaction.
Prédiction de la mobilité d'un usager mobile: objectif, caractéristiques, données et modèles
(CERIST, 2019-12-23) Hocine, Boukhedouma; Meziane, Abdelkrim ; Amel, Benna; Slimane, Hammoudi
De nos jours, nous assistons à une vraie révolution dans le domaine de la génération de données et de l’information, en particulier dans les villes intelligentes. La prédiction de la mobilité nécessite la disponibilité d’une masse importante de données provenant de sources très variées, en particulier lorsqu’il s’agit d’une ville intelligente où les données peuvent être largement collectées. L’accès à ces données peut être soumis à des contraintes et des conditions, le challenge est de pouvoir accéder et récupérer ces données et les structurer dans un format exploitable. La prédiction de la mobilité, nécessite aussi la mise en place ou l’utilisation d’un modèle (ou algorithme) le plus approprié permettant de fournir la meilleure prédiction en termes de précision. Un modèle de prédiction peut être réalisé à l’aide de l’une des techniques dédiées à la prédiction telles que les chaînes de Markov, les Machines Learning et les Réseaux Bayésiens. Dans le présent document, nous mettons l’accent sur certains aspects liées à la prédiction de la mobilité, à savoir les caractéristiques de la prédiction de mobilité, la provenance, le stockage et l’exploitation des données de mobilité. Le rapport présente aussi un aperçu sur un ensemble de travaux proposant des modèles et des algorithmes pour la prédiction de mobilité ainsi qu’une synthèse qui servira à comparer les différents travaux et techniques et à se positionner par rapport à un besoin spécifique.
Knowledge Discovery from Log Data Analysis in a Multi-source Search System based on Deep Cleaning
(CERIST, 2019-07) Lebib, Fatma Zohra; Mellah, Hakima; Meziane, Abdelkrim
In a multi-source search system, understanding users’ interests and behaviour is essential to improve the search and adapt the results according to each user profile. The interesting information characterizing the users can be hidden in large log files, whereas it must be discovered, extracted and analyzed to build an accurate user profile. This paper presents an approach which analyzes the log data of a multi-source search system using the web usage mining techniques. The aim is to capture, model and analyze the behavioural patterns and profiles of users interacting with this system. The proposed approach consists of two major steps, the first step “pre-processing” eliminates the unwanted data from log files based on predefined cleaning rules, and the second step “processing” extracts useful data on user’s previous queries. In addition to the conventional cleaning process that removes irrelevant data from the log file, such as access of multimedia files, error codes and accesses of Web robots, deep cleaning is proposed, which analyzes the queries structure of different sources to further eliminate unwanted data. This allows to accelerate the processing phase. The generated data can be used for personalizing user-system interaction, information filtering and recommending appropriate sources for the needs of each user.
Social Business Process Model Recommender: An MDE approach
(CERIST, 2018-09-26) Khider, Hadjer; Hammoudi, Slimane; Benna, Amel; Meziane, Abdelkrim
with the advent of the social Web (Web 2.0) and the massive use of online social networks (OSNs) (e.g.Facebook, LinkedIn). OSNs have become new opportunity that provides huge Masses of data about users’, rich in their diversity and important in their quantity. Exploring the profiles data among these OSNs attract a great deal of attention among researchers in several research areas: social information retrieval systems, social recommendation systems. Social Recommender Systems aim to generate meaningful recommendations to a collection of users for items that might be interesting for them. In this paper we propose to investigate social recommender systems for improving Business process (BP) models reuse in process models repositories. The recommender system we propose to integrate we called SBPR recommender. SBPR recommender aims to recommend to the users of such repositories BP models for reuse. LinkedIn User profile is the source of social data for SBPR recommender; BP models are target items to be recommended to user. We propose a framework based on Model Driven Engineering (MDE) approach where techniques of models, metamodels, transformation and weaving are used to implement a generic recommendation process.
Visual Data Mining by Virtual Reality for Protein-Protein Interaction Networks
(CERIST, 2018-03-28) Aouaa, Noureddine; Gherbi, Rachid; Meziane, Abdelkrim; Hadjar, Hayat ; Setitra, Insaf
Currently, visualization techniques in the genetic field require a very important modeling phase in terms of resources. Traditional modeling techniques (in two dimensions) are rarely adapted to manage and process this mass of information. To overcome this kind of problem, we propose to use a new graph modeling technique that, used in conjunction with the concept of virtual reality, allows biologists to have a wide visibility through several points of view, thus facilitating them the exploration of massive data. The general principle of our approach is to build a biological network model in the form of a graph with a spatial representation adapted to the visualization of biological networks in a virtual environment. The results show that the improvement of the node distribution algorithm allows a better and more intuitive visualization, compared to the equivalent two-dimensional representations.
Angle Minimization and Graph Analysis for text line segmentation in handwritten documents
(CERIST, 2018-07-08) Setitra, Insaf; Meziane, Abdelkrim
We propose in this paper a novel approach for text line segmentation in handwritten documents. The approach is based on angle minimization and graph analysis for text lines extraction. We apply our approach on images of ICDAR 2013 Handwriting Segmentation Contest, and give details about its robustness against skew and text orientation. We compare the approach to relevant text line segmentation state of art methods, apply it to Algerian manuscripts and report relevant results
WebVR based Interactive Visualization of Open Health Data
(CERIST, 2018-04-22) Hadjar, Hayet; Meziane, Abdelkrim; Guerbi, Rachid; Setitra, Insaf; Zeghichi, Seyf eddine; Lahmil, Abdessalam
Visualization and manipulation of complex and multivariate data in virtual worlds is important for both holders of these data and for their users. Indeed, Virtual Reality helps to make multidimensional data more intelligible and to bring useful information and knowledge. Offering Virtual Reality to browsers, also known as Web Virtual Reality, moreover, simplifies access, multi sharing and manipulation of complex and multivariate data. In this paper, we propose a new system for exploring and visualizing multidimensional data in WebVR. The system implements three methods that we compare based upon several criteria. As the area of application; we use health data that we collect from open data portals.
Les Manuscrits Arabes Anciens En Ligne : Pratiques et Recommandations
(CERIST, 2017-04-10) Habbak, Noureddine; Meziane, Abdelkrim
Les technologies de l’information ont révolutionné la bibliothèque classique. Aujourd’hui, de nombreuses bibliothèques passent au monde numérique. L’accès aux documents qui ont tendance à se détériorer rapidement et qui sont très demandés tels que les manuscrits arabes anciens, devient de plus en plus simple, ce qui assure la conservation des manuscrits et garantit une large diffusion de ces documents. Ce travail consiste à recenser les différentes bibliothèques numériques disposant de ce type de documents selon des critères bien établis et effectuer une étude critique et comparative entre ces institutions afin de dégager ce que doit comporter une bonne bibliothèque numérique des manuscrits arabes.
Fast and smart object proposals for object detection
(CERIST, 2017-05-11) Amrane, Abdesalam; Meziane, Abdelkrim; Boulekrinat, Houda; Atik, Ali
Object localization plays an important role in object detection and classification. In the last years, several methods have shifted from sliding windows techniques to object proposals techniques. The latter produces a small set of windows submitted to an object classifier to reduce the computational time. In this paper, we propose a fast unsupervised method that combines the edge feature and saliency map to generate less than hundred bounding boxes from the processed image. Our approach exploits a number of rules based on edges information plus saliency regions to decide if an object is present in a window. We have carried out several experiments to validate our approach on ImageNet dataset and obtained very promising results.

Research Reports

Browse

Filters

Settings

Sort By

Results per page

Search Results