Browsing by Author "Djerbi, Rachid"

Now showing 1 - 8 of 8

Air quality monitoring using IoT : a survey
(IEEE, 2019) Mokrani, Hocine; Lounas, Razika; Bennai, Mohamed Tahar; Salhi, Dhai Eddine; Djerbi, Rachid
The increase in industrial activities and the rapidurbanization of human populations had a terrible effect onglobal air quality. Thousands of factories and billions of vehiclesrelease enormous amounts of pollutants into the air everyday; dangerously affecting human health. Many epidemiologicalstudies pointed out the responsibility of air pollution in manyhealth issues, the reason why monitoring air quality becamean obligation to prevent or limit these issues. Conventionalsystems based on measuring stations are expensive and offerlow data granularity. As a result, researchers are increasinglytargeting IOT-based systems. However, elaborating a new systemfor air quality monitoring requires an awareness of the stateof the art and the mastery of a certain amount of specificknowledge (pollutants, their health effects, the sensing equipment,the IOT possible configuration,...).This paper aims to answerthese necessities by reviewing the existing works on air qualitymonitoring using IOT with the focus on lasted trends andchallenges
A Collaborative System for Machine Learning-Based Final-Year Projects With Enhanced Dataset Accessibility
(IGI Global, 2024) Lounas, Razika; Djerbi, Rachid; Mokrani, Hocine; Bennai, Mohamed Tahar
This chapter explores the transformative impact of information and communication technology (ICT) on pedagogy, specifically focusing on the integration of collaboration tools in final year projects (FYPs). Final year projects (FYPs) represent the ultimate activity in the student's curriculum. They are designed to use, test, and enhance the knowledge students have gained over the years by confronting them with real-world projects. Despite existing systems for FYPs, the chapter identifies gaps, particularly in covering the entire FYP process and in addressing different collaborative aspects. With a focus on the rise of machine learning-based FYPs, this research aims to propose a comprehensive solution based on a proposed collaboration architecture in response to various needs such as communication, coordination, production, and resource sharing. The application is designed for multiple user roles, including students, advisors, and administrative staff, each allocated a personalized workspace. The novelty of the proposed system is its comprehensive coverage of all collaborative aspects mentioned throughout the FYP process, including proposal processing, project assignment, project completion, and evaluation. The research contributes to fostering innovation in machine learning projects by effectively managing and sharing datasets through collaboration tools. The results indicate good scores in improving collaborative aspects with a score of 98% for virtualization in coordination and 96% for communication. The results also showed that surveyed users are positively inclined to use the system as their final year project (FYP) management system, with an attention-to-use score of 90% of advisors and 92.8% of students.
Communities' Detection in social networks : state of the art and perspectives
(2018) Djerbi, Rachid; Imache, Rabah; Amad, Mourad
Détection des communautés dans les réseaux sociaux
(Université M'hamad Bougara : Faculté des Sciences, 2021) Djerbi, Rachid; Amad, Mourad(Directeur de thèse)
Ces dernières années, plusieurs modèles, approches et algorithmes pour analyser et extraire les connaissances des réseaux sociaux (SN) ont été proposés. L'une des connaissances les plus recherchées dans ce contexte est de trouver le regroupement d'abonnés en ‘’clusters’’ autours des centres d’intérêt et de sujets de discussion. On parle alors du concept social des «communautés». Une communauté est donc un groupe d'abonnés (ou de noeuds dans le contexte graphique) fortement connectés entre eux et faiblement connectés avec les autres. La détection des communautés est devenue une tâche importante pour comprendre comment la structure du SN change avec le temps. C'est également une étape essentielle de l'analyse des SN. Cependant, trouver les communautés d’un réseau social reste un défi et un domaine de recherche d'actualité qui attire de nombreux chercheurs. Dans ce travail, nous proposons une nouvelle approche pour détecter la meilleure partition des communautés en fonction du nombre de noeuds en commun entre chaque paire d'entre eux. En se basant sur la vie sociale des individus au sein de leurs sociétés, nous cherchons l’ensemble des paires (parents) ayant le maximum de noeuds (fils) en commun pour en former une communauté (famille), les autres individus joindront les communautés adéquates selon quelques paramètres de préférences, les communautés trouvées se fusionnent selon quelques conditions. Le modèle proposé est stable, veut dire qu’il donne toujours les mêmes résultats (ou similaires) pour plusieurs exécutions sur le même graphe. Nos expériences sur des vrais SN montrent que l'approche proposée peut définir avec précision l’ensemble des communautés. Le modèle proposé est générique et plusieurs extensions ont été proposé comme la prise en charge des réseaux orientés/non orientés, dynamiques/statiques, pondérés ou non, communautés avec ou sans chevauchement. Dans ce mémoire nous parlons des réseaux sociaux et la détection des communautés, donnons un état de l’art et historique de cet axe de recherche, puis détaillerons notre contribution et nous finissons avec une conclusion et quelques perspectives
Formal Modelling and Implementation of Clark-Wilson Security Policy with FoCaLiZe
(Institute of Electrical and Electronics Engineers, 2024) Haloua, Fatima; Messaoud, Abbas; Djerbi, Rachid; Bouhamed, Mohammed Mounir
The security of every system hinges on a robust policy that orchestrates controls to safeguard the confidentiality, integrity, and accessibility of information. Implementing such a policy requires meticulous formulation grounded in mathematical and logical precision. In this context, we present a formal modeling and implementation of the Clark-Wilson security method using the FoCaLiZe environment, a workshop equipped with certification capabilities, where programming is intertwined with formal proof. The proposed approach enables the specification of the Clark-Wilson policy constraints and security principles as properties and theorems within FoCaLiZe. Thanks to Zenon, the automatic theorem prover of FoCaLiZe, derived properties and theorems that ensure system safety can be checked and proven.
A new model for communities' detection in dynamic social networks inspired from human families
(Inderscience, 2020) Djerbi, Rachid; Amad, Mourad; Imache, Rabah
Nowadays, social networks have been widely used by different people for different purposes in the world. The discovering of communities is a widespread subject in the space of social networks analysis. Many interesting solutions have been proposed in the literature. However, most solutions have common problems: the stability and the community structures quality. In this paper, we propose a new model to find communities based on a new concept called 'large families'. This model will be used, to motivate a community detection strategy to identify and effectively monitor the evolution of dynamic communities. We propose a compromise between the stability and the quality metrics. We apply our model on a real social network of the karate club of Zachary. Also, we describe experiences of our model on a large scale network of Enron's email data set as broader Benchmark Network. Simulations results show that our proposed model is globally satisfactory.
Novel Machine Learning-Driven Road Accident Analysis: A Comparative Study for Predictive Safety and Infrastructure Planning
(2025) Djerbi, Rachid; Bennai, M.Tahar; Boucif, Amine
Road traffic accidents remain a critical global safety concern, demanding proactive rather than reactive mitigation strategies. This paper presents a comprehensive analysis of the U.K. Road Accident dataset, leveraging machine learning to predict accident frequency and uncover contributing factors. We perform extensive data preprocessing and feature engineering to transform raw accident records into a structured format suitable for time-series forecasting. A suite of predictive models, including regularized linear models (Lasso, Ridge), Support Vector Regression (SVR), and Facebook’s Prophet, are trained and rigorously evaluated. Our comparative analysis, based on metrics such as Root Mean Squared Error (RMSE), R-squared, and Mean Absolute Error (MAE), demonstrates that models like Lasso, Prophet, and SVR consistently outperform traditional tree-based methods, achieving R² scores of up to 0.99. The findings highlight the efficacy of machine learning in providing robust predictive insights for proactive road safety interventions and data-informed civil engineering practices. This study offers a valuable framework for leveraging historical data to enhance transportation safety and guide future infrastructure development
Towards a Smart Data Transmission Strategy for IoT Monitoring Systems: Application to Air Quality Monitoring
(IEEE, 2019) Lounas, Razika; Salhi, Dhai Eddine; Mokrani, Hocine; Djerbi, Rachid
In the modern digital area, Internet of Things (IoT) is increasingly gathering attention for the implementation of applications in several aspects of everyday activities, intending to make our cities smarter and more comfortable. Therefore, the implementation of these IoT applications raises several challenges to overcome. One of these challenges is the efficient use of resources at each stage of the application, such as acquisition, storage, processing, and networking. In smart cities, many IoT monitoring systems continuously generate large amounts of data. These data volumes, before they can be processed and responded, must first be transmitted through the city's networks (Wifi, Bluetooth, LTE). To deal with this considerable amount of continually transmitted data and to reduce the load on networks, we propose an approach based on the efficient use of data compression in IoT systems. This approach uses a data compression smart strategy to reduce the transmitted data during the acquisition process and thus minimize the use of network resources while providing the user with relevant information in real-time using a prioritization mechanism. In order to show the efficiency of our proposal, we conducted experiments on a case study of an air quality monitoring system