smart.lab.tunisia@gmail.com +216 71 588 443
Connexion

Ines Thabet

Informations générales

Ines Thabet
Grade

Maître Assistant

Biographie courte

Ines THABET received her PhD in Computer Science from the National School of Computer Sciences (Tunisia) and the University Toulouse I Capitole (France), and her Master Degree in Computer Science from the National School of Applied Sciences of Lyon. She is currently an Assistant Professor at Higher School of Digital Economy, University of Manouba, Tunisia. She is currently a member of the SMART laboratory at the Higher Institute of Management of Tunis. Her current research focuses on multi-agent simulation, deep learning, and machine learning with applications to crisis management.

Axes de recherche

Multi Agent System
Simulation

Publications

  • 2017
    Mohamed Chaawa, Ines Thabet, Chihab Hanachi, Lamjed Ben Said

    Modelling and simulating a crisis management system: an organisational perspective

    Enterprise Information Systems, Volume 11, 2017

    Résumé

    Crises are complex situations due to the dynamism of the environment, its unpredictability and the complexity of the interactions among several different and autonomous involved organisations. In such a context, establishing an organisational view as well as structuring organisations’ communications and their functioning is a crucial requirement. In this article, we propose a multi-agent organisational model (OM) to abstract, simulate and analyse a crisis management system (CMS). The objective is to evaluate the CMS from an organisational view, to assess its strength as well as its weakness and to provide deciders with some recommendations for a more flexible and reactive CMS. The proposed OM is illustrated through a real case study: a snowstorm in a Tunisian region. More precisely, we made the following contribution: firstly, we provide an environmental model that identifies the concepts involved in the crisis. Then, we define a role model that copes with the involved actors. In addition, we specify the organisational structure and the interaction model that rule communications and structure actors’ functioning. Those models, built following the GAIA methodology, abstract the CMS from an organisational perspective. Finally, we implemented a customisable multi-agent simulator based on the  Janus  platform to analyse, through several performed simulations, the organisational model

    Jihene Sassi, Ines Thabet, Khaled Ghedira

    A Framework to Support Tunisian Tweets Analysis for Crisis Management

    ISCRAM-med 2017, 2017

    Résumé

    The increasing crisis frequency and the growing impact of their damages require efficient crisis management processes in order to manage crisis effectively and reduce losses. In such context, the need of accurate and updated information about crises is extremely important. In recent years, crisis information has frequently been provided by social media platforms such as Twitter, Facebook, Flickr, etc. In fact, considering the huge amount of shared information, their precision and their real time characteristic, organizations are moving towards the development of crisis management applications that include information provided by social media platforms. Following this view, the main purpose of our work is to propose a framework for Tunisian tweets extraction and analysis. More precisely, we provide an architecture that includes necessary components and tools for Tunisian dialect treatment. The proposed architecture is an extension on the existing AIDR platform. In addition, we specify the functioning of the proposed architecture to enable firstly terms transliteration from Arabic to Latin alphabet, secondly their normalization and finally their translation in order to be treated by existing social media analysis platform.

  • Ines Thabet, Mohamed Chaawa, Lamjed Ben Said

    A Multi-agent Organizational Model for a Snow Storm Crisis Management

    ISCRAM-med 2014: 143-156, 2014

    Résumé

    This paper introduces an organizational multi-agent model for crisis management. The considered crisis is a heavy snow storm, occurred at a north Tunisian delegation. The studied crisis caused severe infrastructure damages and endangered people’s lives. Crisis systems are generally made of several heterogeneous and autonomousorganizations. Each organization is given tasks and their tasks are strongly correlated. Organizations have to interact frequently and cooperate at a high level to deal with the crisis. In this context, thinking the crisis management at a macro level with an organizational view as well as structuring organizations’ communications and their functioning is a crucial requirement. Following this view, the main purpose of our work is to propose a multi-agent system organization that manages resources efficiently, structure the communication among all the actors involved in the crisis management and orchestrate their work. More precisely, we provide an environment model that identifies all concepts and entities involved in the snow storm crisis. We specify, using GAIA methodology, a multi-agent organizational model that defines the roles involved in the system and the interaction protocols to realize organizational objectives. Finally, a simulator has been implemented to demonstrate the feasibility of our approach.

  • Ines Thabet, Issam Bouslimi, Chihab Hanachi, Khaled Ghedira

    A Multi-agent Organizational Model for Grid Scheduling

    KES-AMSTA 2011: 148-158, 2011

    Résumé

    Multi-agent technology provides high level organizational concepts (groups, roles, commitments, interaction protocols) to structure, coordinate and ease the adaptation of distributed systems efficiently. This paper proposes to model a grid scheduling system as a multi-agent system organization. The resulting organizational model, based on the Agent Group Role meta-model of Ferber, is evaluated at the conceptual and implementation level. At the conceptual level, we evaluate the efficiency, robustness and flexibility of our model. At the implementation level, the analysis and the evaluation of our proposition, done through simulations, show its efficiency.

  • Ines Thabet, Chihab Hanachi, Khaled Ghedira

    Towards an Adaptive Grid Scheduling: Architecture and Protocols Specification

    KES-AMSTA 2009: 599-608, 2009

    Résumé

    Grid is known to be a heterogeneous, distributed and dynamic environment. In order to take fully advantages from grid power, Grid scheduling must take into consideration the environment’s constraints and be adaptive. In this work, Grid architecture is fully rethought in terms of agents in order to implement a cooperative and adaptive scheduling. At a macro level, our architecture enables flexible cooperation among its components using high level interaction protocols. At the micro level, agents in charge of scheduling perform an adaptive behaviour since they are able to perceive their environment and its disturbances, to reason and to deliberate about the actions to undertake in order to adapt. This is made possible by the use of Belief-Desire-Intention mechanisms. For that purpose, we propose a conceptual model useful for the perception function. Also, a typology of adaptive rules useful for the deliberation step is given. Component’s behaviour are specified and simulated with Petri-Nets

  • Ines Thabet, Chihab Hanachi, Khaled Ghedira

    Vers une architecture de type agent BDI pour un ordonnanceur de grille adaptatif

    CAL 2008: 19-33, 2008

    Résumé

    Un Ordonnanceur de Grille (OG) a pour objectif d'optimiser l'utilisation des ressources mises à sa disposition. Le plus souvent, ce composant manque de flexibilité dans sa conception et a des difficultés à s'adapter aux diverses perturbations (fluctuation de la qualité de service, arrivée ou départ de nouvelles ressources, arrivée de travaux prioritaires, etc). L'objectif de cet article est de proposer une architecture orientée agents de type BDI (Belief Desire Intention) pour permettre à l'OG de s'adapter à ces perturbations et de travailler en coopération avec ses accointances. L'OG proposé fonctionne en boucle selon un schéma perception-délibération-action. La perception de l'environnement et de ses perturbations est rendue possible ici à l'aide d'un modèle conceptuel qui décrit à la fois la structure de la Grille et son fonctionnement. La délibération décide des actions à entreprendre (migration d'application, changement de plan d'ordonnancement, changement de politique d'attribution des tâches,..) pour s'adapter aux perturbations sur la base de règles qui proposent différents types d'adaptation selon les événements détectés. L'action correspond à la mise en oeuvre des décisions prises lors de la délibération.