Rim Slama
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Rim Slama has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Hedi Tabia
Université Paris-Saclay Université Paris-Saclay Université Paris-Saclay MIT
3 shared publications - Ahed Alboody
CESI LINEACT
2 shared publications - Amina Kammoun
Sfax University
2 shared publications - Mohamed Abid
Sfax University
2 shared publications - Stefano Berretti
University of Florence
2 shared publications - Tarek Ouni
Sfax University
2 shared publications
Latest Publications
- Open Access
Toward Generalizable State-of-Charge Prediction of Lithium-Ion Batteries Using Deep Learning and Real-World Data
Recently, numerous approaches have been proposed to improve State of Charge (SoC) prediction, demonstrating the potential of deep learning (DL) techniques for accurate battery state estimation. However, most of these methods are validated on laboratory-controlled or synthetic datasets and do not sufficiently consider real-world battery operating conditions. In practice, batteries operate under highly diverse usage patterns, environmental conditions, and user profiles, which can significantly affect SoC estimation accuracy. In this paper, we address this limitation by leveraging real-world data, which contains measurements from vehicle batteries under heterogeneous user behaviors and operating scenarios. The proposed methodology includes a data cleaning and filtering preprocessing stage, followed by an original DL framework designed to evaluate SoC estimation under different learning conditions. The framework is data driven and built upon a TimerV2-based architecture capable of capturing long-term temporal dependencies and nonlinear relationships in battery signals. Furthermore, transfer learning strategies are explored to enhance adaptability across different battery configurations and datasets for efficient knowledge transfer. Extensive experiments show that the proposed approach achieves high estimation accuracy and strong generalization performance, demonstrating its suitability for reliable real-time SoC estimation in practical battery management systems.
Open AccessToward Generalizable State-of-Charge Prediction of Lithium-Ion Batteries Using Deep Learning and Real-World Data
Recently, numerous approaches have been proposed to improve State of Charge (SoC) prediction, demonstrating the potential of deep learning (DL) techniques for accurate battery state estimation. However, most of these methods are validated on laboratory-controlled or synthetic datasets and do not sufficiently consider real-world battery operating conditions. In practice, batteries operate under highly diverse usage patterns, environmental conditions, and user profiles, which can significantly affect SoC estimation accuracy. In this paper, we address this limitation by leveraging real-world data, which contains measurements from vehicle batteries under heterogeneous user behaviors and operating scenarios. The proposed methodology includes a data cleaning and filtering preprocessing stage, followed by an original DL framework designed to evaluate SoC estimation under different learning conditions. The framework is data driven and built upon a TimerV2-based architecture capable of capturing long-term temporal dependencies and nonlinear relationships in battery signals. Furthermore, transfer learning strategies are explored to enhance adaptability across different battery configurations and datasets for efficient knowledge transfer. Extensive experiments show that the proposed approach achieves high estimation accuracy and strong generalization performance, demonstrating its suitability for reliable real-time SoC estimation in practical battery management systems.
- Open Access
- 25 April 2026
- Published by Elsevier in SSRN Electronic Journal
Traffic Signal Control with Extended Perception for Enhanced Robustness andResilience Using Graph Attention and Temporal Encoders
Deep Reinforcement Learning has demonstrated significant potential in optimizing Traffic Signal Control; however, existing Multi-Agent approaches often struggle with the non-stationarity inherent to abnormal traffic conditions. Most models, trained in nominal simulation environments, lack the resilience to withstand unforeseen disturbances such as sensor failures, road blockages, or extreme weather. To address this gap, this paper proposes a robust Spatio-Temporal Graph Reinforcement Learning framework explicitly designed for structural stability. Our architecture facilitates intelligent inter-agent collaboration by selectively weighting relevant neighbors via a Graph Attention Network (GATv2), while a Transformer-based Temporal Interaction Encoder captures long-term historical trends. This dual mechanism enables agents to distinguish between transient noise and persistent failure patterns, facilitating proactive rather than reactive control. Furthermore, we introduce a rigorous stress-testing benchmark comprising stochastic perturbation scenarios; ranging from high-frequency random blockages to critical arterial collapses, to quantify system resilience. Extensive experiments on a stochastic grid network demonstrate that our approach not only achieves superior throughput under high-demand nominal conditions but also exhibits exceptional resilience, recovering stable traffic flow significantly faster than state-of-the-art baselines following severe structural disruptions.
- 25 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessTraffic Signal Control with Extended Perception for Enhanced Robustness andResilience Using Graph Attention and Temporal Encoders
Deep Reinforcement Learning has demonstrated significant potential in optimizing Traffic Signal Control; however, existing Multi-Agent approaches often struggle with the non-stationarity inherent to abnormal traffic conditions. Most models, trained in nominal simulation environments, lack the resilience to withstand unforeseen disturbances such as sensor failures, road blockages, or extreme weather. To address this gap, this paper proposes a robust Spatio-Temporal Graph Reinforcement Learning framework explicitly designed for structural stability. Our architecture facilitates intelligent inter-agent collaboration by selectively weighting relevant neighbors via a Graph Attention Network (GATv2), while a Transformer-based Temporal Interaction Encoder captures long-term historical trends. This dual mechanism enables agents to distinguish between transient noise and persistent failure patterns, facilitating proactive rather than reactive control. Furthermore, we introduce a rigorous stress-testing benchmark comprising stochastic perturbation scenarios; ranging from high-frequency random blockages to critical arterial collapses, to quantify system resilience. Extensive experiments on a stochastic grid network demonstrate that our approach not only achieves superior throughput under high-demand nominal conditions but also exhibits exceptional resilience, recovering stable traffic flow significantly faster than state-of-the-art baselines following severe structural disruptions.
- 5 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 7 (4) , 780-793
Optimizing Hand Gesture Recognition With an Accurate Graph Model and Mixture of Experts for Joint Relationships and Temporal Dynamics
Hand gesture recognition approaches have recently achieved promising results by extracting spatial and temporal features. However, existing methods often miss the relationships between distant joints and are hindered by high computational costs. In this article, we introduce a novel graph-based model for hand gesture recognition that overcomes these limitations by efficiently capturing dependencies between distant joints within a unified semantic space and requiring less computation time. Our model consists of three main components: the Mixture of Experts (MoE) framework, which dynamically selects specialized sub-models focused on joints, bones, and motion features to optimize performance and efficiency; the Graph Hierarchical Edge Representation (GHER), which captures multi-scale relationships between joints and models both local and global interactions within the hand skeleton; and the Light Graph Temporal Fusion Transformer (LGTFT), which integrates an attention-based graph transformer with a lightweight Gated Recurrent Unit (GRU) to efficiently capture temporal dynamics, while reducing computational costs. We validate the proposed model through extensive experiments on three benchmark hand gesture recognition datasets: IPN, SHREC’17, and Briareo. Our approach achieves superior results when compared to state-of-the-art methods, while reducing computational time.
- 5 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 7 (4) , 780-793
Optimizing Hand Gesture Recognition With an Accurate Graph Model and Mixture of Experts for Joint Relationships and Temporal Dynamics
Hand gesture recognition approaches have recently achieved promising results by extracting spatial and temporal features. However, existing methods often miss the relationships between distant joints and are hindered by high computational costs. In this article, we introduce a novel graph-based model for hand gesture recognition that overcomes these limitations by efficiently capturing dependencies between distant joints within a unified semantic space and requiring less computation time. Our model consists of three main components: the Mixture of Experts (MoE) framework, which dynamically selects specialized sub-models focused on joints, bones, and motion features to optimize performance and efficiency; the Graph Hierarchical Edge Representation (GHER), which captures multi-scale relationships between joints and models both local and global interactions within the hand skeleton; and the Light Graph Temporal Fusion Transformer (LGTFT), which integrates an attention-based graph transformer with a lightweight Gated Recurrent Unit (GRU) to efficiently capture temporal dynamics, while reducing computational costs. We validate the proposed model through extensive experiments on three benchmark hand gesture recognition datasets: IPN, SHREC’17, and Briareo. Our approach achieves superior results when compared to state-of-the-art methods, while reducing computational time.
- 12 May 2025
- Published by Springer Nature
- p. 169-185
GSK-C2F: Graph Skeleton Modelization for Action Segmentation and Recognition Using a Coarse-to-Fine Strategy
- 12 May 2025
- Published by Springer Nature
- p. 169-185
GSK-C2F: Graph Skeleton Modelization for Action Segmentation and Recognition Using a Coarse-to-Fine Strategy
- 12 May 2025
- Published by Springer Nature
- p. 53-68
Hand Gesture Recognition Using Dual Graph Hierarchical Edges Representation and Graph Transformer Network
- 12 May 2025
- Published by Springer Nature
- p. 53-68
Hand Gesture Recognition Using Dual Graph Hierarchical Edges Representation and Graph Transformer Network
- 5 March 2025
- Published by Springer Nature
- p. 83-97
PMoET: Going Wider Than Deeper Using the Parallel Mixture of Experts Transformer for 3D Hand Gesture Recognition
- 5 March 2025
- Published by Springer Nature
- p. 83-97
PMoET: Going Wider Than Deeper Using the Parallel Mixture of Experts Transformer for 3D Hand Gesture Recognition
- 31 July 2024
- Published by Springer Nature
- p. 317-336
Graph Transformer Mixture-of-Experts (GTMoE) for 3D Hand Gesture Recognition
- 31 July 2024
- Published by Springer Nature
- p. 317-336
Graph Transformer Mixture-of-Experts (GTMoE) for 3D Hand Gesture Recognition
- 4 February 2023
- Published by Springer Nature
- p. 131-143
FNR-GAN: Face Normalization and Recognition with Generative Adversarial Networks
- 4 February 2023
- Published by Springer Nature
- p. 131-143
FNR-GAN: Face Normalization and Recognition with Generative Adversarial Networks
- Open Access
- 3 December 2022
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 55 (5) , 1-37
Generative Adversarial Networks for Face Generation: A Survey
Recently, generative adversarial networks (GANs) have progressed enormously, which makes them able to learn complex data distributions in particular faces. More and more efficient GAN architectures have been designed and proposed to learn the different variations of faces, such as cross pose, age, expression, and style. These GAN-based approaches need to be reviewed, discussed, and categorized in terms of architectures, applications, and metrics. Several reviews that focus on the use and advances of GAN in general have been proposed. However, to the best of our knowledge, the GAN models applied to the face, which we call facial GANs , have never been addressed. In this article, we review facial GANs and their different applications. We mainly focus on architectures, problems, and performance evaluation with respect to each application and used datasets. More precisely, we review the progress of architectures and discuss the contributions and limits of each. Then, we expose the encountered problems of facial GANs and propose solutions to handle them. Additionally, as GAN evaluation has become a notable current defiance, we investigate the state-of-the-art quantitative and qualitative evaluation metrics and their applications. We conclude this work with a discussion on the face generation challenges and propose open research issues.
- 3 December 2022
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 55 (5) , 1-37
Open AccessGenerative Adversarial Networks for Face Generation: A Survey
Recently, generative adversarial networks (GANs) have progressed enormously, which makes them able to learn complex data distributions in particular faces. More and more efficient GAN architectures have been designed and proposed to learn the different variations of faces, such as cross pose, age, expression, and style. These GAN-based approaches need to be reviewed, discussed, and categorized in terms of architectures, applications, and metrics. Several reviews that focus on the use and advances of GAN in general have been proposed. However, to the best of our knowledge, the GAN models applied to the face, which we call facial GANs , have never been addressed. In this article, we review facial GANs and their different applications. We mainly focus on architectures, problems, and performance evaluation with respect to each application and used datasets. More precisely, we review the progress of architectures and discuss the contributions and limits of each. Then, we expose the encountered problems of facial GANs and propose solutions to handle them. Additionally, as GAN evaluation has become a notable current defiance, we investigate the state-of-the-art quantitative and qualitative evaluation metrics and their applications. We conclude this work with a discussion on the face generation challenges and propose open research issues.
- Open Access
Machine Learning Identifies Chronic Low Back Pain Patients from an Instrumented Trunk Bending and Return Test
Nowadays, the better assessment of low back pain (LBP) is an important challenge, as it is the leading musculoskeletal condition worldwide in terms of years of disability. The objective of this study was to evaluate the relevance of various machine learning (ML) algorithms and Sample Entropy (SampEn), which assesses the complexity of motion variability in identifying the condition of low back pain. Twenty chronic low-back pain (CLBP) patients and 20 healthy non-LBP participants performed 1-min repetitive bending (flexion) and return (extension) trunk movements. Analysis was performed using the time series recorded by three inertial sensors attached to the participants. It was found that SampEn was significantly lower in CLBP patients, indicating a loss of movement complexity due to LBP. Gaussian Naive Bayes ML proved to be the best of the various tested algorithms, achieving 79% accuracy in identifying CLBP patients. Angular velocity of flexion movement was the most discriminative feature in the ML analysis. This study demonstrated that: supervised ML and a complexity assessment of trunk movement variability are useful in the identification of CLBP condition, and that simple kinematic indicators are sensitive to this condition. Therefore, ML could be progressively adopted by clinicians in the assessment of CLBP patients.
Open AccessMachine Learning Identifies Chronic Low Back Pain Patients from an Instrumented Trunk Bending and Return Test
Nowadays, the better assessment of low back pain (LBP) is an important challenge, as it is the leading musculoskeletal condition worldwide in terms of years of disability. The objective of this study was to evaluate the relevance of various machine learning (ML) algorithms and Sample Entropy (SampEn), which assesses the complexity of motion variability in identifying the condition of low back pain. Twenty chronic low-back pain (CLBP) patients and 20 healthy non-LBP participants performed 1-min repetitive bending (flexion) and return (extension) trunk movements. Analysis was performed using the time series recorded by three inertial sensors attached to the participants. It was found that SampEn was significantly lower in CLBP patients, indicating a loss of movement complexity due to LBP. Gaussian Naive Bayes ML proved to be the best of the various tested algorithms, achieving 79% accuracy in identifying CLBP patients. Angular velocity of flexion movement was the most discriminative feature in the ML analysis. This study demonstrated that: supervised ML and a complexity assessment of trunk movement variability are useful in the identification of CLBP condition, and that simple kinematic indicators are sensitive to this condition. Therefore, ML could be progressively adopted by clinicians in the assessment of CLBP patients.