Samia Yahyaoui
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Samia Yahyaoui has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Rached Ben Hassen
Laboratory of Materials and Environment for Sustainable Development, LR18ES10, ISSBAT, University of Tunis El Manar, 9 Street Zouheir Essafi, Tunis 1006, Tunisia
3 shared publications Abdelhamid Ben Salah
Lab. Sci. Mater. Environ., Fac. Sci. Sfax, 3018 Sfax, Tunisia
2 shared publications- Afrah Alanazi
Department of Information Systems, College of Computer and Information Sciences, Jouf University, Sakaka 72388, Saudi Arabia
2 shared publications - Karim Gasmi
Department of Computer Science, College of Computer and Information Sciences, Jouf University, Sakaka, Saudi Arabia
2 shared publications - Sahar Almenwer
Department of Computer Science, College of Computer and Information Sciences, Jouf University, Sakaka 72388, Saudi Arabia
2 shared publications A. Ben Salah
1 shared publication
Latest Publications
- Open Access
- 15 April 2026
- Published by MDPI AG in Biomedicines
- Vol. 14 (4) , 898
CT-Malaria Detection via Adaptive-Weighted Deep Learning Models
Context: In numerous low- and middle-income nations, malaria remains a significant issue due to the challenges associated with diagnosing it through thin blood smears. The appearance of images can vary significantly depending on the microscope type, magnification, lighting conditions, slide preparation methods, and staining techniques. Due to the delicate morphology of parasites, false negatives might adversely affect patient care. Objective: To achieve optimal outcomes from validation, it is essential to construct a robust and easily replicable process. This pipeline should integrate the optimal elements of classical machine learning and end-to-end deep learning, enhance reliability by pairwise ensembling, and select ensemble weights in a logical, data-driven manner. Method: To achieve our objective, we propose two tracks. The initial track encompasses real-time augmentation, convolution-based feature extraction, and the training of calibrated classical classifiers. The second module focuses on training many convolutional networks from inception to completion. Subsequently, we construct paired ensembles and employ a hybrid methodology to select convex weights for combining the findings. This method initially evaluates a set of candidate weights and then refines them to maximise validation accuracy. Results: The precision of the two-track architecture consistently improves, transitioning from conventional baselines to end-to-end models. Optimal and consistent enhancements are achieved through weighted ensembling. Utilising optimised fusion reduces the incidence of false negatives for subtle parasites and false positives caused by staining artefacts. This yields an accuracy of 96.35% on the reserved data and reduced variance across folds. Conclusions: The integration of augmentation, multiple modelling tracks, and optimal pairwise ensembling yields the highest accuracy in categorising malaria smears. It facilitates further enhancements by incorporating supplementary models, multi-class extensions, and operating-point calibration.
- 15 April 2026
- Published by MDPI AG in Biomedicines
- Vol. 14 (4) , 898
Open AccessCT-Malaria Detection via Adaptive-Weighted Deep Learning Models
Context: In numerous low- and middle-income nations, malaria remains a significant issue due to the challenges associated with diagnosing it through thin blood smears. The appearance of images can vary significantly depending on the microscope type, magnification, lighting conditions, slide preparation methods, and staining techniques. Due to the delicate morphology of parasites, false negatives might adversely affect patient care. Objective: To achieve optimal outcomes from validation, it is essential to construct a robust and easily replicable process. This pipeline should integrate the optimal elements of classical machine learning and end-to-end deep learning, enhance reliability by pairwise ensembling, and select ensemble weights in a logical, data-driven manner. Method: To achieve our objective, we propose two tracks. The initial track encompasses real-time augmentation, convolution-based feature extraction, and the training of calibrated classical classifiers. The second module focuses on training many convolutional networks from inception to completion. Subsequently, we construct paired ensembles and employ a hybrid methodology to select convex weights for combining the findings. This method initially evaluates a set of candidate weights and then refines them to maximise validation accuracy. Results: The precision of the two-track architecture consistently improves, transitioning from conventional baselines to end-to-end models. Optimal and consistent enhancements are achieved through weighted ensembling. Utilising optimised fusion reduces the incidence of false negatives for subtle parasites and false positives caused by staining artefacts. This yields an accuracy of 96.35% on the reserved data and reduced variance across folds. Conclusions: The integration of augmentation, multiple modelling tracks, and optimal pairwise ensembling yields the highest accuracy in categorising malaria smears. It facilitates further enhancements by incorporating supplementary models, multi-class extensions, and operating-point calibration.
- Open Access
- 8 January 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (2) , 204
Early Tuberculosis Detection via Privacy-Preserving, Adaptive-Weighted Deep Models
Background: Tuberculosis (TB) is a significant global health issue, particularly in resource-limited regions where radiological expertise is constrained. This project aims to develop a scalable deep learning system that safeguards privacy and achieves high accuracy in the early identification of tuberculosis using chest X-ray images. The objective is to implement federated learning with an adaptive-weighted ensemble optimised by a Genetic Algorithm (GA) to address the challenges of centralised training and single-model approaches. Method: We developed an ensemble learning method that combines multiple locally trained models to improve diagnostic consistency and reduce individual-model bias. An optimisation system that autonomously selected the optimal ensemble weights determined each model’s contribution to the final decision. A controlled augmentation process was employed to enhance the model’s robustness and reduce the likelihood of overfitting by introducing realistic alterations to appearance, geometry, and acquisition conditions. Federated learning facilitated collaboration among universities for training while ensuring data privacy was maintained during the establishment of the optimal ensemble at each location. In this system, just model parameters were transmitted, excluding patient photographs. This enabled the secure amalgamation of global data without revealing sensitive clinical information. Standard diagnostic metrics, including accuracy, sensitivity, precision, F1 score, AUC, and confusion matrices, were employed to evaluate the model’s performance. Results: The proposed federated, GA-optimized ensemble demonstrated superior performance compared with individual models and fixed-weight ensembles. The system achieved 98% accuracy, 97% F1 score, and 0.999 AUC, indicating highly reliable discrimination between TB-positive and typical cases. Federated learning preserved model robustness across heterogeneous data sources, while ensuring complete patient privacy. Conclusions: The proposed federated, GA-optimized ensemble achieves highly accurate and robust early tuberculosis detection while preserving patient privacy across distributed clinical sites. This scalable framework demonstrates strong potential for reliable AI-assisted TB screening in resource-limited healthcare settings.
- 8 January 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (2) , 204
Open AccessEarly Tuberculosis Detection via Privacy-Preserving, Adaptive-Weighted Deep Models
Background: Tuberculosis (TB) is a significant global health issue, particularly in resource-limited regions where radiological expertise is constrained. This project aims to develop a scalable deep learning system that safeguards privacy and achieves high accuracy in the early identification of tuberculosis using chest X-ray images. The objective is to implement federated learning with an adaptive-weighted ensemble optimised by a Genetic Algorithm (GA) to address the challenges of centralised training and single-model approaches. Method: We developed an ensemble learning method that combines multiple locally trained models to improve diagnostic consistency and reduce individual-model bias. An optimisation system that autonomously selected the optimal ensemble weights determined each model’s contribution to the final decision. A controlled augmentation process was employed to enhance the model’s robustness and reduce the likelihood of overfitting by introducing realistic alterations to appearance, geometry, and acquisition conditions. Federated learning facilitated collaboration among universities for training while ensuring data privacy was maintained during the establishment of the optimal ensemble at each location. In this system, just model parameters were transmitted, excluding patient photographs. This enabled the secure amalgamation of global data without revealing sensitive clinical information. Standard diagnostic metrics, including accuracy, sensitivity, precision, F1 score, AUC, and confusion matrices, were employed to evaluate the model’s performance. Results: The proposed federated, GA-optimized ensemble demonstrated superior performance compared with individual models and fixed-weight ensembles. The system achieved 98% accuracy, 97% F1 score, and 0.999 AUC, indicating highly reliable discrimination between TB-positive and typical cases. Federated learning preserved model robustness across heterogeneous data sources, while ensuring complete patient privacy. Conclusions: The proposed federated, GA-optimized ensemble achieves highly accurate and robust early tuberculosis detection while preserving patient privacy across distributed clinical sites. This scalable framework demonstrates strong potential for reliable AI-assisted TB screening in resource-limited healthcare settings.
- Open Access
- 26 March 2025
- Published by AIP Publishing in Journal of Applied Physics
- Vol. 137 (12)
Simulation of the magnetic and magnetocaloric effect by means of theoretical models in La0.52Dy0.15Pb0.33MnO3 compound
This study investigates the magnetic behavior and magnetocaloric properties of the La0.52Dy0.15Pb0.33MnO3 perovskite compound through a simple analysis based on theoretical modeling. Using the mean field theory and the Bean–Rodbell model, we analyze the effect of Dy substitution on magnetic ordering and the magnetocaloric response. The Curie temperature is modeled using a Gaussian distribution to assess the impact of applied fields on magnetic entropy change (−ΔSM). The results indicate that synthesis conditions influence the broadening and softening of the (−ΔSM) peak, attributed to the structural inhomogeneities in polycrystalline materials. Our findings highlight the significant role of Dy doping in tuning the magnetocaloric effect, offering insights into the development of more efficient magnetic refrigeration materials.
- 26 March 2025
- Published by AIP Publishing in Journal of Applied Physics
- Vol. 137 (12)
Open AccessSimulation of the magnetic and magnetocaloric effect by means of theoretical models in La0.52Dy0.15Pb0.33MnO3 compound
This study investigates the magnetic behavior and magnetocaloric properties of the La0.52Dy0.15Pb0.33MnO3 perovskite compound through a simple analysis based on theoretical modeling. Using the mean field theory and the Bean–Rodbell model, we analyze the effect of Dy substitution on magnetic ordering and the magnetocaloric response. The Curie temperature is modeled using a Gaussian distribution to assess the impact of applied fields on magnetic entropy change (−ΔSM). The results indicate that synthesis conditions influence the broadening and softening of the (−ΔSM) peak, attributed to the structural inhomogeneities in polycrystalline materials. Our findings highlight the significant role of Dy doping in tuning the magnetocaloric effect, offering insights into the development of more efficient magnetic refrigeration materials.
- Open Access
- 26 August 2004
- Published by International Union of Crystallography (IUCr) in Acta Crystallographica Section A Foundations of Crystallography
- Vol. 60 (a1) , s279
[Yb(H2O)8][Cd3Cl9(H2O)]·6H2O
- 26 August 2004
- Published by International Union of Crystallography (IUCr) in Acta Crystallographica Section A Foundations of Crystallography
- Vol. 60 (a1) , s279
Open Access[Yb(H2O)8][Cd3Cl9(H2O)]·6H2O
- 8 January 2004
- Published by Wiley in ChemInform
- Vol. 35 (4)
[Yb(H2O)8] [Cd3Cl9(H2O)]×6H2O.
For Abstract see ChemInform Abstract in Full Text.
- 8 January 2004
- Published by Wiley in ChemInform
- Vol. 35 (4)
[Yb(H2O)8] [Cd3Cl9(H2O)]×6H2O.
For Abstract see ChemInform Abstract in Full Text.
- 25 July 2003
- Published by Wiley in ChemInform
- Vol. 34 (31)
Crystal Structure and Electrical Behavior of the New Ceramic Ba0.7Na0.3Ti0.7Nb0.3O3 .
For Abstract see ChemInform Abstract in Full Text.
- 25 July 2003
- Published by Wiley in ChemInform
- Vol. 34 (31)
Crystal Structure and Electrical Behavior of the New Ceramic Ba0.7Na0.3Ti0.7Nb0.3O3 .
For Abstract see ChemInform Abstract in Full Text.