Yesma Bendaha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yesma Bendaha has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Abdelali Benali
University of Science and Technology of Oran Mohamed Boudiaf-Faculty of Electrical Engineering-Department of Automation, Oran, Algeria
1 shared publication - Bachir Daaou1 shared publication
- Kadda Boumediene1 shared publication
- Malika Seddik Bouchouicha
University of Science and Technology of Oran Mohamed Boudiaf-Faculty of Mechanical Engineering-Department of Marine Engineering, Oran, Algeria
1 shared publication - Rachid Rimani
University of Mustapha Stambouli of Mascara, Mascara, Algeria
1 shared publication - Zakaria Bellahcene
University of Science and Technology of Oran Mohamed Boudiaf-Faculty of Electrical Engineering-Department of Automation, Oran, Algeria
1 shared publication
Latest Publications
- 24 September 2026
- Published by Instituto Mexicano de Tecnologia del Agua in Tecnología y ciencias del agua
WaterFormer-MS: A multi-stream deep learning framework for surface water segmentation from satellite imagery
Accurate mapping of surface water bodies is essential for dam monitoring, irrigation planning, and sustainable water resource management. Conventional methods based on spectral indices, such as NDWI, can face challenges in complex environments due to spectral ambiguity, seasonal variability, and urban or vegetated surfaces. Deep learning approaches such as U-Net and DeepLabv3+ have improved water-body segmentation; however, accurately delineating fine boundaries and detecting small water bodies remain challenging. To address these limitations, this study proposes WaterFormer-MS, a multi-stream deep learning framework for surface water segmentation from Sentinel-2 imagery. The architecture integrates spectral, geometric, and contextual information through dedicated processing streams and combines the extracted features using a convolutional fusion module enhanced with CBAM attention. This design aims to improve feature representation and support accurate water-body delineation. The proposed model was trained and evaluated using Sentinel-2 imagery from a publicly available Kaggle dataset containing diverse land-cover conditions, including urban, vegetated, and agricultural environments. At 300 epochs, WaterFormer-MS achieved an overall accuracy of 97.4%, a precision of 93.2%, a recall of 94.2%, an F1-score of 93.7%, and an IoU of 89.7%. Within the experimental framework, WaterFormer-MS achieved higher values than the other proposed variants. Comparisons with conventional NDWI-based approaches and published deep learning methods suggest competitive performance; however, these comparisons should be interpreted cautiously because datasets, preprocessing procedures, training protocols, and evaluation settings may differ. The results support the potential of the proposed framework for surface water segmentation and environmental monitoring applications in diverse remote sensing scenarios.
- 24 September 2026
- Published by Instituto Mexicano de Tecnologia del Agua in Tecnología y ciencias del agua
WaterFormer-MS: A multi-stream deep learning framework for surface water segmentation from satellite imagery
Accurate mapping of surface water bodies is essential for dam monitoring, irrigation planning, and sustainable water resource management. Conventional methods based on spectral indices, such as NDWI, can face challenges in complex environments due to spectral ambiguity, seasonal variability, and urban or vegetated surfaces. Deep learning approaches such as U-Net and DeepLabv3+ have improved water-body segmentation; however, accurately delineating fine boundaries and detecting small water bodies remain challenging. To address these limitations, this study proposes WaterFormer-MS, a multi-stream deep learning framework for surface water segmentation from Sentinel-2 imagery. The architecture integrates spectral, geometric, and contextual information through dedicated processing streams and combines the extracted features using a convolutional fusion module enhanced with CBAM attention. This design aims to improve feature representation and support accurate water-body delineation. The proposed model was trained and evaluated using Sentinel-2 imagery from a publicly available Kaggle dataset containing diverse land-cover conditions, including urban, vegetated, and agricultural environments. At 300 epochs, WaterFormer-MS achieved an overall accuracy of 97.4%, a precision of 93.2%, a recall of 94.2%, an F1-score of 93.7%, and an IoU of 89.7%. Within the experimental framework, WaterFormer-MS achieved higher values than the other proposed variants. Comparisons with conventional NDWI-based approaches and published deep learning methods suggest competitive performance; however, these comparisons should be interpreted cautiously because datasets, preprocessing procedures, training protocols, and evaluation settings may differ. The results support the potential of the proposed framework for surface water segmentation and environmental monitoring applications in diverse remote sensing scenarios.
- 24 March 2026
- Published by Bialystok University of Technology in Acta Mechanica et Automatica
- Vol. 20 (1)
A Comparative Study of Conventional and Advanced PI Controllers for Induction Motor Speed Regulation under Parameter Variations
This paper presents a comparative study of various Proportional-Integral (PI) controller strategies applied to the speed regulation of a squirrel-cage induction motor under Indirect Field-Oriented Control (IFOC). The classical PI controller is benchmarked against three enhanced versions: the Hyperbolic PI (HPI), the Variable Gain PI (VGPI), and the Anti-Windup PI. Each controller is evaluat-ed in terms of dynamic response, steady-state error, robustness to parameter variations and disturbance rejection. In addition, var-ious numerical simulations under MATLAB/Simulink are carried out to evaluate the motor’s performance through different operating conditions, including load disturbances and reference speed changes. The obtained numerical results conclude that, among the modified PI variants, the VGPI and Anti-Windup PI demonstrate superior performance in terms of robustness, adaptability, and transient behaviour. The obtained numerical results highlight the advantages and limitations of the control strategy, providing valu-able insights for selecting an appropriate speed regulator in industrial applications.
- 24 March 2026
- Published by Bialystok University of Technology in Acta Mechanica et Automatica
- Vol. 20 (1)
A Comparative Study of Conventional and Advanced PI Controllers for Induction Motor Speed Regulation under Parameter Variations
This paper presents a comparative study of various Proportional-Integral (PI) controller strategies applied to the speed regulation of a squirrel-cage induction motor under Indirect Field-Oriented Control (IFOC). The classical PI controller is benchmarked against three enhanced versions: the Hyperbolic PI (HPI), the Variable Gain PI (VGPI), and the Anti-Windup PI. Each controller is evaluat-ed in terms of dynamic response, steady-state error, robustness to parameter variations and disturbance rejection. In addition, var-ious numerical simulations under MATLAB/Simulink are carried out to evaluate the motor’s performance through different operating conditions, including load disturbances and reference speed changes. The obtained numerical results conclude that, among the modified PI variants, the VGPI and Anti-Windup PI demonstrate superior performance in terms of robustness, adaptability, and transient behaviour. The obtained numerical results highlight the advantages and limitations of the control strategy, providing valu-able insights for selecting an appropriate speed regulator in industrial applications.