Salma Azzouzi

We present a streamlined PCA-PSO structure of lightweight face recognition in this paper, which combines principal component analysis (PCA) to reduce dimensions with particle swarm optimization (PSO) to adaptively select features. In contrast to traditional PCA-based models, our model dynamically chooses the most informative subset of the 44 features and results in a small but informative representation. The approach has a high recognition accuracy of 99.99 on ORL and 98.45 on LFW, with low latency (approximately 3 seconds per epoch) and low memory footprint, and without the need to use a graphic card to run it. Extensive computational studies have shown that the proposed pipeline is much faster and consumes less memory than PCA-ACO and lightweight convolutional neural network (CNN) models like MobileNetV2 and Squeeze Net and is best suited to run in real-time in CPU-limited environments. The statistical tests prove the betterment of our method compared to the past methods, where the changes are statistically significant. This research offers an efficient, simple, yet scalable alternative to deep learning-based recognition systems, especially when embedded integration is a key requirement, by offering rapid convergence, adaptive feature selection, and compact representation.

As part of a successful IoV implementation, testing of IoV-based systems is essential for detecting errors related to device availability, communication reliability, quality of service, and system security. However, this remains a challenge due to the dynamic nature of IoV susceptibility to failures, heterogeneity, and large data streams associated with remotely distributed IoV system components. This paper proposes an intelligent agent-based architecture with a special focus on semantic interoperability testing in order to ensure better interaction and coherence between the various components of the IoV-based system. As a proof of concept, the proposed architecture is implemented in the NetLogo (v6.4.0) multi-agent environment and applied to a case study that detects semantic interoperability issues at both the data and query levels.

Obesity is ranked as one of the biggest health challenges facing humanity today. Globally, the number of obese people has almost tripled since 1975, and this lifestyle disease currently affects hundreds of millions of adults who suffer from major health problems due to it, such as heart disease, type 2 diabetes and some cancers, that weigh heavily on the global health systems, In order to keep high standards for methods, anthropometric variables, i.e., Height and Weight have been intentionally excluded from the features, because labels for obesity classes are based on these measurements; thus, including them would introduce target leakage. All models were individually tuned with Optuna (50 trials, TPE sampler), and the class imbalance was managed by the synthetic minority over-sampling technique (SMOTE), which was done only in training folds. The models were evaluated by stratified five-fold cross-validation, with the macro-averaged F1-score being used as the main metric for evaluation. The best model was the fine-tuned XGBoost, which gave a test macro F1-score value of 0.872 and a macro-AUC of 0.977. The model was higher performing than others such as Random Forest (F1 = 0.869), MLP (F1 = 0.777), and Logistic Regression (F1 = 0.605). This means that behavioral and lifestyle variables may have a very strong and sufficient signal to identify obesity status, even when there are no direct anthropometric measurements available. However, it is worth noting that results here represent only performance on a single public benchmark dataset, so they cannot be taken as proof that the model would do well in real-world clinical settings. With the advent of ML methods for obesity prediction, rigorous, leakage-free evaluation becomes indispensable. Apart from external validation of the clinical models on independent datasets, the use of interpretability tools such as SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) for understanding decision-making, as well as sex and gender subgroup analyses for evaluating fairness and equity, should also be pursued in the future. This study highlights the importance of rigorous, leakage-free evaluation in machine learning-based obesity research. Future work should focus on external validation using independent clinical cohorts, the integration of interpretability techniques such as SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), and subgroup analyses by sex and gender to assess model fairness and clinical equity.

The rapid expansion of the Internet of Things (IoT) has brought forth numerous challenges in testing distributed applications within cloud environments. A significant issue is the latency associated with hosting these applications on cloud computing platforms, despite their potential to improve productivity and reduce costs. This necessitates a reevaluation of existing conformance testing frameworks for cloud environments, with a focus on addressing coordination and observability challenges during data processing. To tackle these challenges, this study proposes a novel approach based on Deep Q-Networks (DQN) and federated learning (FL). In this model, fog nodes train their local models independently and transmit only parameter updates to a central server, where these updates are aggregated into a global model. The DQN agents replace explicit coordination messages with learned decision functions, dynamically determining when and how testers should coordinate. This approach not only preserves the privacy of IoT devices but also enhances the efficiency of the testing process. We provide a comprehensive mathematical formulation of our approach, along with a detailed case study of a Smart City Traffic Management System. Our experimental results demonstrate significant improvements over traditional testing approaches, including a ~58% reduction in coordination messages. These findings confirm the effectiveness of our approach for distributed testing in dynamic environments with varying network conditions.

In modern e-learning environments, ensuring both student identity verification and concentration monitoring during online examinations has become increasingly important. This paper introduces a robust sequential framework that integrates Generative Adversarial Networks (GANs), Convolutional Neural Networks (CNNs) and fuzzy logic to achieve reliable face recognition and interpretable attentiveness assessment. Images from the Extended Yale B (cropped) dataset are preprocessed through grayscale normalization and resizing, while GANs generate synthetic variations in pose, illumination, and occlusion to enrich the training set and improve generalization. The CNN extracts discriminative facial features for identity recognition, and a fuzzy inference system transforms the CNN’s confidence scores into human-interpretable concentration levels. To stabilize learning and prevent overfitting, the model incorporates dropout regularization, batch normalization, and extensive data augmentation. Comprehensive evaluations using confusion matrices, ROC–AUC, and precision–recall analyses demonstrate an accuracy of 98.42%. The proposed framework offers a scalable and interpretable solution for secure and reliable online exam proctoring.

Background/Objectives: Cardiovascular diseases (CVDs) remain the primary cause of mortality worldwide, underscoring the critical importance of developing accurate early prediction models. In this study, we propose an advanced stacking ensemble learning framework to improve the predictive performance for CVD diagnosis. Methods: The methodology encompasses comprehensive data preprocessing, feature selection, cross-validation, and the construction of a stacking architecture integrating Random Forest (RF), Support Vector Machine (SVM), and CatBoost as base learners. Two meta-learning configurations were examined: Logistic Regression (LR) and a Multilayer Perceptron (MLP). Results: Experimental results indicate that the MLP-based stacking model achieves superior performance, with an accuracy of 97.06%, outperforming existing approaches reported in the literature. Furthermore, the model demonstrates high recall (96.08%) and precision (98%), confirming its robustness and generalization capacity. Conclusions: Compared to individual classifiers and traditional ensemble methods, the proposed approach yields significantly enhanced predictive outcomes, highlighting the potential of deep learning-based stacking strategies in cardiovascular risk assessment.

Currently, massive open online courses (MOOCs) are experiencing major developments and arebecoming increasingly popular in distance learning programs. The goal is to break down inequalitiesand disseminate knowledge to everyone by creating a space for exchange and interaction.Despite the improvements to this educational model, MOOCs still have low retention rates, whichcan be attributed to a variety of factors, including learners’ heterogeneity. The paper aims toaddress the issue of low retention rates in MOOCs by introducing an innovative prediction modelthat provides the best (optimal) learning path for at-risk learners. For this purpose, learners at riskof dropping out are identified, and their courses are adapted to meet their needs and skills. A casestudy is presented to validate the effectiveness of our approach using classification algorithms forprediction and the ant colony optimization (ACO) algorithm to optimize learners’ paths.