RBRohallah Benaboud

Rohallah Benaboud

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Rohallah Benaboud has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    FedDPA: Dynamic Prototypical Alignment for Federated Learning with Non-IID Data

    by Oussama Akram Bensiah, Rohallah Benaboud

    Federated learning (FL) has emerged as a powerful framework for decentralized model training, preserving data privacy by keeping datasets localized on distributed devices. However, data heterogeneity, characterized by significant variations in size, statistical distribution, and composition across client datasets, presents a persistent challenge that impairs model performance, compromises generalization, and delays convergence. To address these issues, we propose FedDPA, a novel framework that utilizes dynamic prototypical alignment. FedDPA operates in three stages. First, it computes class-specific prototypes for each client to capture local data distributions, integrating them into an adaptive regularization mechanism. Next, a hierarchical aggregation strategy clusters and combines prototypes from similar clients, which reduces communication overhead and stabilizes model updates. Finally, a contrastive alignment process refines the global model by enforcing intra-class compactness and inter-class separation in the feature space. These mechanisms work in concert to mitigate client drift and enhance global model performance. We conducted extensive evaluations on standard classification benchmarks—EMNIST, FEMNIST, CIFAR-10, CIFAR-100, and Tiny-ImageNet 200—under various non-identically and independently distributed (non-IID) scenarios. The results demonstrate the superiority of FedDPA over state-of-the-art methods, including FedAvg, FedNH, and FedROD. Our findings highlight FedDPA’s enhanced effectiveness, stability, and adaptability, establishing it as a scalable and efficient solution to the critical problem of data heterogeneity in federated learning.


  • Open Access

    TSO-Optimized Weighted Soft Voting Ensemble of Pretrained CNNs for MRI-Based Brain Tumor Classification

    by Ahmed Zahrouri, Smaine Mazouzi, Rohallah Benaboud

    Early detection and accurate classification of brain tumors from MRI scans remain critical challenges in modern healthcare. This paper develops a novel hybrid approach that leverages Tuna Swarm Optimization (TSO) to optimize ensemble weights in a weighted soft voting framework for brain tumor classification. Our methodology applies TSO specifically to optimize the contribution weights of four pretrained Convolutional Neural Network architectures (InceptionV3, ResNet152V2, ResNet50V2, and Xception) in an ensemble framework. TSO, inspired by the collective hunting behavior of tuna fish, offers superior exploration capabilities and faster convergence than traditional optimization algorithms for weight optimization, while weighted soft voting enables probability-based integration of diverse model predictions. The proposed approach was trained and tested using a comprehensive dataset of 7,023 MRI images from the Nickparvar dataset, classifying brain scans into four classes: healthy, gliomas, pituitary tumors, and meningiomas. Transfer learning with fine-tuning was applied to the four pretrained CNN models, with TSO dynamically adjusting the ensemble contribution weights through spiral and parabolic foraging behaviors to minimize classification error. The weighted soft voting mechanism then combined these TSO-optimized weights with probability distributions to produce robust predictions. This hybrid TSO-optimized ensembleapproach achieved a validation accuracy of 99.92% and F1-score of 99.92%, superior to all individual models (best individual: ResNet50V2 at 99.69%) and conventional soft voting ensemble methods (99.85%). The optimized weight distribution prioritized ResNet50V2 (0.456) and Xception (0.342), demonstrating the algorithm’s ability to identify complementary model strengths. The improved performance and computational efficiency of the proposed framework position it as a promising clinical decision support tool for accelerating diagnosis processes and enhancing treatment planning in brain tumor assessment.


  • Open Access

    Formal Verification of the Correctness and Soundness of a Pomset-to-LTS Transformation Algorithm

    by Asma Bezza, Rohallah Benaboud, Toufik-Messaoud Maarouk, Rabea Ameur-Boulifa

    In this paper, we present a comprehensive proof of the correctness and soundness of our previously published algorithm for transforming partially ordered multisets (Pomsets) into labeled transition systems (LTS). Our approach rigorously ensures that the transformation algorithm preserves the behavioral semantics of the original Pomset, ensuring that the resulting LTS accurately represents the concurrent and sequential dependencies inherent in the Pomset. We employ Hoare logic to formally verify the correctness of the algorithm, proving that every valid Pomset is transformed into a corresponding LTS without loss of information. Additionally, we provide detailed proofs of soundness, showing that the algorithm produces an LTS if and only if the input is a valid Pomset. This algorithm was initially proposed as part of our new refinement proof approach, which has already been published. However, the correctness of the algorithm had not been formally proven until now. These results confirm the reliability and robustness of our transformation algorithm, making it a valuable tool for modeling and analyzing concurrent systems.

  • Open Access

    Binary Tuna Swarm Optimization Algorithm-Based Feature Selection for Intrusion Detection Systems

    by Abdelouaheb Khiar, Smaine Mazouzi, Rohallah Benaboud, Hichem Haouassi

    Feature selection is crucial for improving intrusion detection systems by addressing the curse of dimensionality and eliminating irrelevant features. However, applying continuous metaheuristics—such as the Tuna Swarm Optimization (TSO) algorithm—to this inherently binary problem requires effective binarization strategies. This paper presents TUNA-FS, a novel feature selection framework that employs a binary variant of the TSO algorithm. The proposed method introduces an adaptive V-shaped transfer function that dynamically manages the binarization process, maintaining a balance between exploration and exploitation throughout the search. Additionally, a multi-objective fitness function is used to jointly optimize key objectives: enhancing detection accuracy, reducing false alarms, and minimizing the number of selected features. The effectiveness of the approach is validated through comprehensive experiments on the NSL-KDD and CIC-IDS2017 benchmark datasets. Results demonstrate that the method achieves substantial feature reduction while maintaining high detection performance across multiple classifiers, including support vector machines, decision trees, random forests, and k-nearest neighbors. Comparative analysis against state-of-the-art methods confirms the competitiveness and balanced performance of the proposed framework, positioning it as an effective technique for enhancing intrusion detection efficiency and accuracy.


  • Open Access

    Towards Dynamic Reconfiguration of a Composite Web Service: An Approach Based on QoS Prediction

    by Abdessalam Messiaid, Farid Mokhati, Rohallah Benaboud, Hajer Salem

    Service-oriented architecture provides the ability to combine several web services in order to fulfil a user-specific requirement. In dynamic environments, the appearance of several unforeseen events can destabilize the composite web service (CWS) and affect its quality. To deal with these issues, the composite web service must be dynamically reconfigured. Dynamic reconfiguration may be enhanced by avoiding the invocation of degraded web services by predicting QoS for the candidate web service. In this paper, we propose a dynamic reconfiguration method based on HMM (Hidden Markov Model) states to predict the imminent degradation in QoS and prevent the invocation of partner web services with degraded QoS values. PSO (Particle Swarm Optimization) and SFLA (Shuffled Frog Leaping Algorithm) are used to improve the prediction efficiency of HMM. Through extensive experiments on a real-world dataset, WS-Dream, the results demonstrate that the proposed approach can achieve better prediction accuracy. Moreover, we carried out a case study where we revealed that the proposed approach outperforms several state-of-the-art methods in terms of execution time.