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

Lilia Rejeb

Informations générales

Lilia Rejeb
Grade

Maître de conférences

Équipes

Axes de recherche

Artificial Intelligence
Machine Learning
Multi Agent System
Optimization

Publications

  • 2025
    Hajer Alaya, Lilia Rejeb, Lamjed Ben Said

    Explanable AI in automatic sleep scoring: A review

    Hajer ALAYA, Lilia Rejeb, Lamjed Ben Said, “Explainable AI in automatic sleep scoring: A review”, International Conference on Intelligence in Business and Industry 2025 (IBI'25) 24 et 25 avril 2025., 2025

    Résumé

    The application of Artificial Intelligence (AI) in
    automatic sleep scoring presents significant opportunities for
    enhancing sleep analysis and diagnosing sleep disorders.
    However, a major challenge lies in the lack of transparency in
    AI-driven decision-making, which can hinder trust and
    comprehension among sleep researchers and clinicians.
    Explainable Artificial Intelligence (XAI) has emerged as a key
    approach to addresss these concerns by providing insights into
    AI model predictions and improving interpretability. This
    review examines the role and effectiveness of Explainability and
    interpretability in automatic sleep scoring, analyzing key
    challenges, the impact of various methodologies, and commonly
    used algorithms. Based on a comprehensive analysis of 100
    recent studies, we bridge the gap between computer-readable
    data encodings and human-understandable information,
    enhancing model explainability and transparency. Ultimately,
    this review underscores the vital role of Explainability in
    refining sleep evaluation and decision-making, emphasizing the
    necessity of further research to address existing challenges and
    maximize its potential.

  • Lilia Rejeb, Abir Chaabani, Hajer Safi, Lamjed Ben Said

    Multimodal freight transport optimization based on economic and ecological constraint

    . In: Alharbi, I., Ben Ncir, CE., Alyoubi, B., Ben-Romdhane, H. (eds) Advances in Computational Logistics and Supply Chain Analytics. Unsupervised and Semi-Supervised Learning. Springer, Cha, 2024

    Résumé

    The increasing demand for efficient global supply chain management and faster product delivery has led to a rise in the use of multimodal transportation systems (MFT). One of the key challenges in multimodal transportation is selecting the appropriate freight mode. This decision depends on several factors such as cost, transit time, reliability, mode availability, service frequency, and cargo characteristics. However, existing research often focuses on only two modes, namely trucks and trains, which fails to capture the complexities of real-world freight transportation decisions. Moreover, while reducing travel time and cost are primary objectives for service providers and researchers, other important considerations such as environmental impact are often overlooked. To this end, in this work, the researchers take into account four major modes of transportation (Air, Road, Rail, and Sea/Water) in a multimodal freight context aiming to optimize three distinct objectives: overall transportation cost, transportation time, and CO2 emissions. To solve this problem, the researchers adopt two the well-known metaheuristic algorithms: Tabu Search and the Genetic Algorithm through an experimental study demonstrating the efficacy of these evolutionary solution methods in tackling such challenging optimization problems.

    Ghofrane Ben Hammouda, Lilia Rejeb, Lamjed Ben Said

    Ensemble learning for multi-channel sleep stage classification

    Biomedical Signal Processing and Control, 93, 106184., 2024

    Résumé

    Sleep is a vital process for human well-being. Sleep scoring is performed by experts using polysomnograms, that record several body activities, such as electroencephalograms (EEG), electrooculograms (EOG), and electromyograms (EMG). This task is known to be exhausting, biased, time-consuming, and prone to errors. Current automatic sleep scoring approaches are mostly based on single-channel EEG and do not produce explainable results. Therefore, we propose a heterogeneous ensemble learning-based approach where we combine accuracy-based learning classifier systems with different algorithms to produce a robust, explainable, and enhanced classifier. The efficiency of our approach was evaluated using the Sleep-EDF benchmark dataset. The proposed models have reached an accuracy of 89.2% for the stacking model and 87.9% for the voting model, on a multi-class classification task based on the R&K guidelines.

  • Wiem Zaouga, Lilia Rejeb, Latifa Rabai

    Tailoring project management practices for decision making: an in-depth comparative study

    International Journal of Project Organisation and ManagementVol. 15, No. 2, pp 158-183. DOI: 10.1504/IJPOM.2023.131677, 2023

    Résumé

    The efforts to successfully complete projects lead to the development of various project management (PM) standards, best practices and guidelines, issued by different organisational bodies. These PM practices, when appropriately implemented, lead to a better project performance. However, studies on how to adopt and adapt such practices according to management needs, remain limited. In this paper, we are going to focus on how to map the project requirements with the suitable PM practices to support the PM decision making. To respond this question, we put forward an in-depth comparative study amongst the well-established PM practices considering a set of features to pick out their challenges, limits as well as their applicability. Through this comparison, we extend the discussion of PM practices features by contrasting them to three distinct categories of requirements which are technical, contextual and behavioural. This analysis allows us to map each category to its corresponding practice(s). Our finding provides comprehensive recommendation guidelines to both practitioners and researchers in order to improve their decision making in line with the project environment.

  • Syrine Ben Abbes, Lilia Rejeb, Lassaad Baati

    Route planning for electric vehicles

    IET Intell. Transp. Syst. 16, 875–889 (2022). https://doi.org/10.1049/itr2.12182, 2022

    Résumé

    This work addresses the multi-objective route planning and charging problem for Battery Electric Vehicles (BEVs). The proposed solution is based on the NSGA-II algorithm to derive the Pareto-optimal set of eco-routes with the minimum travel and charging time, distance, energy consumption and charging costs while complying with the constraints related to the battery State of Charge (SoC) and the status of charging stations. Influencing factors, such as, vehicle and battery parameters, weather conditions, driver behaviour, road grade, Time Of Use (TOU) electricity cost, and Charging Stations (CS) status and type, are taken into account. The final results of the proposed method are compared with the well-established simulator SUMO.

    Meriem Sebai, Lilia Rejeb, Mohamed-ali Denden, Yasmine Amor, Lassaad Baati, Lamjed Ben Said

    Optimal electric vehicles route planning with traffic flow prediction and real-time traffic incidents

    International Journal of Electrical and Computer Engineering Research, 2(1), 1–12. doi:10.53375/ijecer.2022.93, 2022

    Résumé

    Electric Vehicles (EVs) are regarded to be among the most environmentally and economically efficient transportation solutions. However, barriers and range limitations hinder this technology’s progress and deployment. In this paper, we examine EV route planning to derive optimal routes considering energy consumption by analyzing historical trajectory data. More specifically, we propose a novel approach for EV route planning that considers real-time traffic incidents, road topology, charging station locations during battery failure, and finally, traffic flow prediction extracted from historical trajectory data to generate energy maps. Our approach consists of four phases: the off-line phase which aims to build the energy graph, the application of the A* algorithm to deliver the optimal EV path, the NEAT trajectory clustering which aims to produce dense trajectory clusters for a given period of the day, and finally, the on-line phase based on our algorithm to plan an optimal EV path based on real traffic incidents, dense trajectory clusters, road topology information, vehicle characteristics, and charging station locations. We set up experiments on real cases to establish the optimal route for electric cars, demonstrating the effectiveness and efficiency of our proposed algorithm.

    Nada Mohammed Murad, Lilia Rejeb, Lamjed Ben Said

    The use of DCNN for road path detection and segmentation

    Iraqi Journal for Computer Science and Mathematics: Vol. 3: Iss. 2, Article 13. DOI: https://doi.org/10.52866/ijcsm.2022.02.01.013, 2022

    Résumé

    In this study, various organizations that have participated in several road path-detecting experimentsare analyzed. However, the majority of techniques rely on attributes or form models built by humans to identifysections of the path. In this paper, a suggestion was made regarding a road path recognition structure that is dependenton a deep convolutional neural network. A tiny neural network has been developed to perform feature extraction toa massive collection of photographs to extract the suitable path feature. The parameters obtained from the model ofthe route classification network are utilized in the process of establishing the parameters of the layers that constitutethe path detection network. The deep convolutional path discovery network’s production is pixel-based and focuseson the identification of path types and positions. To train it, a detection failure job is provided. Failure in pathclassification and regression are the two components that make up a planned detection failure function. Instead oflaborious postprocessing, a straightforward solution to the problem of route marking can be found using observedpath pixels in conjunction with a consensus of random examples. According to the findings of the experiments, theclassification precision of the network for classifying every kind is higher than 98.3%. The simulation that was trainedusing the suggested detection failure function is capable of achieving an accuracy of detection that is 85.5% over atotal of 30 distinct scenarios on the road

    Hiba Chaher, Lilia Rejeb, Lamjed Ben Said

    A behaviorist agent model for the simulation of the human behavior

    International Multi-Conference on: “Organization of Knowledge and Advanced Technologies” (OCTA), Tunis, Tunisia, 2020, pp. 1-11, doi: 10.1109/OCTA49274.2020.9151655., 2022

    Résumé

    Recent researches on computational modeling show that emotions have a major influence on human behavior and decision making. Therefore, it is recognized that they are necessary to produce human-like in artificial agents. Several computational behavior models have been proposed. However, some of them have incorporated the emotion, others have integrated the psychological aspects in order to study the human behavior, but they did not take into account both of the emotional and the psychological impacts. In this context, we attempt to present an overview of the existent works. Then, we aim to present a new behavior agent model that integrates both of the psychological and emotional aspects to prove their impacts on the human decision.

    Nada Mohammed Murad, Lilia Rejeb, Lamjed Ben Said

    Computing driver tiredness and fatigue in automobile via eye tracking and body movements

    Periodicals of Engineering and Natural Sciences (PEN), 10(1), 573. doi:10.21533/pen.v10i1.2705., 2022

    Résumé

    The aim of this paper is to classify the driver tiredness and fatigue in automobile via eye tracking and body movements using deep learning based Convolutional Neural Network (CNN) algorithm. Vehicle driver face localization serves as one of the most widely used real-world applications in fields like toll control, traffic accident scene analysis, and suspected vehicle tracking. The research proposed a CNN classifier for simultaneously localizing the region of human face and eye positioning. The classifier, rather than bounding rectangles, gives bounding quadrilaterals, which gives a more precise indication for vehicle driver face localization. The adjusted regions are preprocessed to remove noise and passed to the CNN classifier for real time processing. The preprocessing of the face features extracts connected components, filters them by size, and groups them into face expressions. The employed CNN is the well-known technology for human face recognition. One we aim to extract the facial landmarks from the frames, we will then leverage classification models and deep learning based convolutional neural networks that predict the state of the driver as 'Alert' or 'Drowsy' for each of the frames extracted. The CNN model could predict the output state labels (Alert/Drowsy) for each frame, but we wanted to take care of sequential image frames as that is extremely important while predicting the state of an individual. The process completes, if all regions have a sufficiently high score or a fixed number of retries are exhausted. The output consists of the detected human face type, the list of regions including the extracted mouth and eyes with recognition reliability through CNN with an accuracy of 98.57% with 100 epochs of training and testing.

    Khaoula Hantous, Lilia Rejeb, Rahma Helali

    Detecting physiological needs using deep inverse reinforcement learning

    Applied Artificial Intelligence: AAI, 36(1), 1–25. doi:10.1080/08839514.2021.2022340,, 2022

    Résumé

    Smart health-care assistants are designed to improve the comfort of the patient where smart refers to the ability to imitate the human intelligence to facilitate his life without, or with limited, human intervention. As a part of this, we are proposing a new Intelligent Communication Assistant capable of detecting physiological needs by following a new efficient Inverse Reinforcement learning algorithm designed to be able to deal with new time-recorded states. The latter processes the patient’s environment data, learns from the patient previous choices and becomes capable of suggesting the right action at the right time. In this paper, we took the case study of Locked-in Syndrome patients, studied their actual communication methods and tried to enhance the existing solutions by adding an intelligent layer. We showed that by using Deep Inverse Reinforcement Learning using Maximum Entropy, we can learn how to regress the reward amount of new states from the ambient environment recorded states. After that, we can suggest the highly rewarded need to the target patient. Also, we proposed a full architecture of the system by describing the pipeline of the information from the ambient environment to the different actors.

    Oussama Kebir, Issam Nouaouri, Lilia Rejeb, Lamjed Ben Said

    Atipreta: An analytical model for time-dependent prediction of terrorist attacks

    International Journal of Applied Mathematics and Computer Science (AMCS), 32(3), 495-510 . doi: 10.34768/amcs-2022-0036, 2022

    Résumé

    In counter-terrorism actions, commanders are confronted with difficult and important challenges. Their decision-making processes follow military instructions and must consider the humanitarian aspect of the mission. In this paper, we aim to respond to the question: What would the casualties be if governmental forces reacted in a given way with given resources? Within a similar context, decision-support systems are required due to the variety and complexity of modern attacks as well as the enormous quantity of information that must be treated in real time. The majority of mathematical models are not suitable for real-time events. Therefore, we propose an analytical model for a time-dependent prediction of terrorist attacks (ATiPreTA). The output of our model is consistent with casualty data from two important terrorist events known in Tunisia: Bardo and Sousse attacks. The sensitivity and experimental analyses show that the results are significant. Some operational insights are also discussed.

  • Meriem Sebai, Ezzeddine Fatnassi, Lilia Rejeb

    A honeybee mating optimization algorithm for solving the static bike rebalancing problem

    Proceedings of the Genetic and Evolutionary Computation Conference Companion, ACM. Presented at the GECCO ’19: Genetic and Evolutionary Computation Conference, ACM New York (pp. 77-78). Prague Czech Republic. doi:10.1145/3319619, 2019

    Résumé

    This paper proposes a new approach to solve the Bike Rebalancing Problem (BRP) based on the Honey-Bee Mating Optimization (HBMO) algorithm. The aim is to reduce the overall traveling cost of redistribution operations under various constraints. The performance of the proposed algorithm is evaluated using a set of benchmark instances for the BRP. Preliminary results are obtained and showed that the proposed approach is promising.

  • Chedi Abdelkarim, Lilia Rejeb, Lamjed Ben Said, Maha Elarbi

    Evidential learning classifier system

    In Proceedings of the Genetic and Evolutionary Computation Conference Companion (pp. 123-124), 2017

    Résumé

    During the last decades, Learning Classifier Systems have known many advancements that were highlighting their potential to resolve complex problems. Despite the advantages offered by these algorithms, it is important to tackle other aspects such as the uncertainty to improve their performance. In this paper, we present a new Learning Classifier System (LCS) that deals with uncertainty in the class selection in particular imprecision. Our idea is to integrate the Belief function theory in the sUpervised Classifier System (UCS) for classification purpose. The new approach proved to be efficient to resolve several classification problems.

    Chedy Abdelkarim, Lilia Rejeb, Lamjed Ben Said, Maha Elarbi

    Evidential learning classifier system

    Authors: Chedi Abdelkarim, Lilia Rejeb, Lamjed Ben Said, Maha ElarbiAuthors Info & Claims GECCO '17: Proceedings of the Genetic and Evolutionary Computation Conference Companion Pages 123 - 124 https://doi.org/10.1145/3067695.3075997, 2017

    Résumé

    During the last decades, Learning Classifier Systems have known many advancements that were highlighting their potential to resolve complex problems. Despite the advantages offered by these algorithms, it is important to tackle other aspects such as the uncertainty to improve their performance. In this paper, we present a new Learning Classifier System (LCS) that deals with uncertainty in the class selection in particular imprecision. Our idea is to integrate the Belief function theory in the sUpervised Classifier System (UCS) for classification purpose. The new approach proved to be efficient to resolve several classification problems.

  • Lilia Rejeb, Zahia Guessoum, Rym M'Hallah

    An Adaptive Approach for the Exploration-Exploitation Dilemma for Learning Agents

    Rejeb, L., Guessoum, Z., M’Hallah, R. (2005)In: Pěchouček, M., Petta, P., Varga, L.Z. (eds) Multi-Agent Systems and Applications IV. CEEMAS 2005. Lecture Notes in Compute, 2005

    Résumé

    Learning agents have to deal with the exploration-exploitation
    dilemma. The choice between exploration and exploitation is very difficult in
    dynamic systems; in particular in large scale ones such as economic systems.
    Recent research shows that there is neither an optimal nor a unique solution for
    this problem. In this paper, we propose an adaptive approach based on meta-rules
    to adapt the choice between exploration and exploitation. This new adaptive approach relies on the variations of the performance of the agents. To validate the
    approach, we apply it to economic systems and compare it to two adaptive methods: one local and one global. Herein, we adapt these two methods, which were
    originally proposed by Wilson, to economic systems. Moreover, we compare different exploration strategies and focus on their influence on the performance of
    the agents

  • Zahia Guessoum, Lilia Rejeb, Rodolphe Durand

    Using adaptive multi-agent systems to simulate economic models

    Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004., New York, NY, USA, 2004, pp. 68-75., 2004

    Résumé

    Economic markets are complex systems. They are characterized by a large and dynamic population of firms. To deal with this complexity, we propose an adaptive multiagent system which models a set of firms in competition with each other within a shared market. The firms are represented by agents; each firm is represented by an adaptive agent. We show the advantages of adaptive agents to represent firms. Moreover, we underline the limits of the economic models which account for the firms only and ignore the organizational forms. We propose a new adaptive multiagent model that includes the organizational forms into the economic models. We simulate this model and discuss its advantages.

Projets