Azeddine Mouhsen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Azeddine Mouhsen has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Abdelhadi Radouane
Hassan first university
7 shared publications - Lhoucine Ben Taleb
Hassan First University of Settat
5 shared publications - Aissam Lyazidi
Sciences and Engineering of Biomedicals, Biophysics and Health Laboratory, Higher Institute of Health Sciences (ISSS), University Hassan 1st, Settat 26002, Morocco
4 shared publications - Badreddine Labakoum
Energy-Materials-Instrumentation and Telecom Laboratory (EMIT), Faculty of Science and Technology, University Hassan 1st, Settat, Morocco
4 shared publications - Ilias En-Naoui
Hassan first university
4 shared publications - Mohammed Harmouchi
Hassan first university
4 shared publications
Latest Publications
- Open Access
- 9 May 2026
- Published by Poltekkes Kemenkes Surabaya in Journal of Electronics, Electromedical Engineering, and Medical Informatics
- Vol. 8 (3) , 1204-1223
BackMix-Enhanced Semi-Supervised Learning for Automated Detection of Aortic Stenosis from Transthoracic Echocardiographic Images
Aortic stenosis (AS) is a prevalent and progressive valvular heart disease requiring accurate severity assessment for optimal clinical decision-making. Transthoracic echocardiography (TTE) is the standard diagnostic modality; however, its interpretation remains operator-dependent and subject to inter-observer variability. In this study, we propose an anatomically guided BackMix-enhanced semi-supervised learning framework for automated echocardiographic view classification and AS severity assessment. The approach leverages Gradient-weighted Class Activation Mapping (Grad-CAM) to preserve diagnostically relevant anatomical regions during augmentation while modifying background areas to mitigate shortcut learning. A semi-supervised self-training strategy combined with an ensemble classification framework was used to exploit both labeled and unlabeled data. The framework was evaluated on the TMED2 dataset of echocardiography, comprising 24,964 TTE images. To assess generalizability, external validation was performed on an independent dataset of 300 cardiologist-labeled echocardiographic images, including apical four-chamber (A4C), parasternal long-axis (PLAX), and parasternal short-axis (PSAX) views. Experimental results demonstrated that the proposed method outperformed the baseline semi-supervised model, improving view classification accuracy by approximately 3% and AS severity classification accuracy by 4–6%, with the largest gain observed in moderate AS. Performance remained consistent on the external validation dataset, supporting the robustness of the proposed approach. Statistical analysis confirmed the significance of these improvements (p < 0.01). Grad-CAM evaluation further demonstrated improved localization of clinically relevant regions. These findings suggest that anatomically guided BackMix augmentation combined with semi-supervised ensemble learning can improve classification accuracy, robustness, and interpretability in echocardiographic analysis under limited annotation conditions, offering a promising approach for automated AS assessment across independent clinical datasets
- 9 May 2026
- Published by Poltekkes Kemenkes Surabaya in Journal of Electronics, Electromedical Engineering, and Medical Informatics
- Vol. 8 (3) , 1204-1223
Open AccessBackMix-Enhanced Semi-Supervised Learning for Automated Detection of Aortic Stenosis from Transthoracic Echocardiographic Images
Aortic stenosis (AS) is a prevalent and progressive valvular heart disease requiring accurate severity assessment for optimal clinical decision-making. Transthoracic echocardiography (TTE) is the standard diagnostic modality; however, its interpretation remains operator-dependent and subject to inter-observer variability. In this study, we propose an anatomically guided BackMix-enhanced semi-supervised learning framework for automated echocardiographic view classification and AS severity assessment. The approach leverages Gradient-weighted Class Activation Mapping (Grad-CAM) to preserve diagnostically relevant anatomical regions during augmentation while modifying background areas to mitigate shortcut learning. A semi-supervised self-training strategy combined with an ensemble classification framework was used to exploit both labeled and unlabeled data. The framework was evaluated on the TMED2 dataset of echocardiography, comprising 24,964 TTE images. To assess generalizability, external validation was performed on an independent dataset of 300 cardiologist-labeled echocardiographic images, including apical four-chamber (A4C), parasternal long-axis (PLAX), and parasternal short-axis (PSAX) views. Experimental results demonstrated that the proposed method outperformed the baseline semi-supervised model, improving view classification accuracy by approximately 3% and AS severity classification accuracy by 4–6%, with the largest gain observed in moderate AS. Performance remained consistent on the external validation dataset, supporting the robustness of the proposed approach. Statistical analysis confirmed the significance of these improvements (p < 0.01). Grad-CAM evaluation further demonstrated improved localization of clinically relevant regions. These findings suggest that anatomically guided BackMix augmentation combined with semi-supervised ensemble learning can improve classification accuracy, robustness, and interpretability in echocardiographic analysis under limited annotation conditions, offering a promising approach for automated AS assessment across independent clinical datasets
- 3 February 2026
- Published by Springer Nature
- p. 467-478
Implementation of a Secure and Smart Three-Phase Energy Monitoring System for Residential Applications
- 3 February 2026
- Published by Springer Nature
- p. 467-478
Implementation of a Secure and Smart Three-Phase Energy Monitoring System for Residential Applications
- Open Access
- 1 December 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 16 (4) , 2605-2614
Design and DSP-based validation of a cascaded DSOGI-PLL for mitigating grid disturbances
Ensuring a smooth power injection into an electric grid in the presence of imperfections, such as phase disturbances, voltage imbalance, frequency variations, harmonics, and DC offsets, requires fast and robust phase-locked loop (PLL) techniques. Among these, the double second-order generalized integrator (DSOGI)-based PLL is widely used due to its strong performance in challenging grid conditions. However, conventional DSOGI-PLL has limitations in handling DC offsets and harmonic disturbances. To address these challenges, this paper introduces the design of a cascaded DSOGI-PLL that enhances attenuation of DC components and low-order harmonics while maintaining computational simplicity for DSP-based implementation. Experimental validation on a TMS320F28379D DSP platform demonstrates that the proposed scheme achieves synchronization settling within 48 ms even under severely polluted grid conditions, while reducing output unit-vector THD to 0.5% when the input voltage contains 22% THD. These results confirm the cascaded DSOGI-PLL as a significant improvement over conventional PLLs.
- 1 December 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 16 (4) , 2605-2614
Open AccessDesign and DSP-based validation of a cascaded DSOGI-PLL for mitigating grid disturbances
Ensuring a smooth power injection into an electric grid in the presence of imperfections, such as phase disturbances, voltage imbalance, frequency variations, harmonics, and DC offsets, requires fast and robust phase-locked loop (PLL) techniques. Among these, the double second-order generalized integrator (DSOGI)-based PLL is widely used due to its strong performance in challenging grid conditions. However, conventional DSOGI-PLL has limitations in handling DC offsets and harmonic disturbances. To address these challenges, this paper introduces the design of a cascaded DSOGI-PLL that enhances attenuation of DC components and low-order harmonics while maintaining computational simplicity for DSP-based implementation. Experimental validation on a TMS320F28379D DSP platform demonstrates that the proposed scheme achieves synchronization settling within 48 ms even under severely polluted grid conditions, while reducing output unit-vector THD to 0.5% when the input voltage contains 22% THD. These results confirm the cascaded DSOGI-PLL as a significant improvement over conventional PLLs.
- Open Access
- 1 December 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 15 (6) , 5091-5105
Nonlinear backstepping and model predictive control for grid-connected permanent magnet synchronous generator wind turbines
This research investigates and compares two nonlinear current-control strategies, backstepping control (BSC) and finite control set model predictive control (FCS-MPC) for machine-side and grid-side converters in grid-connected direct-drive permanent magnet synchronous generator (DD-PMSG) wind turbines. Addressing the control challenges in wind energy systems with varying speeds, the study aims to determine which strategy offers superior performance under identical operating conditions. The nonlinear BSC regulates stator and grid currents using Lyapunov-based techniques, while FCS-MPC leverages model predictions to select optimal switching states based on a cost function. A comprehensive simulation using MATLAB/Simulink is conducted, analyzing each controller’s transient behavior, steady-state response, torque ripple, and power quality total harmonic distortion (THD). Results show that FCS-MPC achieves faster convergence, lower overshoot, and superior power quality compared to BSC, though it requires higher computational resources. Statistical validation supports the robustness of FCS-MPC under parameter uncertainties. This work contributes a structured comparison of advanced nonlinear strategies for PMSG-based wind turbines and provides a foundation for future implementations in real-time embedded control systems. Future directions include experimental validation and hybrid model predictive controller- artificial intelligence (MPC-AI) control frameworks.
- 1 December 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 15 (6) , 5091-5105
Open AccessNonlinear backstepping and model predictive control for grid-connected permanent magnet synchronous generator wind turbines
This research investigates and compares two nonlinear current-control strategies, backstepping control (BSC) and finite control set model predictive control (FCS-MPC) for machine-side and grid-side converters in grid-connected direct-drive permanent magnet synchronous generator (DD-PMSG) wind turbines. Addressing the control challenges in wind energy systems with varying speeds, the study aims to determine which strategy offers superior performance under identical operating conditions. The nonlinear BSC regulates stator and grid currents using Lyapunov-based techniques, while FCS-MPC leverages model predictions to select optimal switching states based on a cost function. A comprehensive simulation using MATLAB/Simulink is conducted, analyzing each controller’s transient behavior, steady-state response, torque ripple, and power quality total harmonic distortion (THD). Results show that FCS-MPC achieves faster convergence, lower overshoot, and superior power quality compared to BSC, though it requires higher computational resources. Statistical validation supports the robustness of FCS-MPC under parameter uncertainties. This work contributes a structured comparison of advanced nonlinear strategies for PMSG-based wind turbines and provides a foundation for future implementations in real-time embedded control systems. Future directions include experimental validation and hybrid model predictive controller- artificial intelligence (MPC-AI) control frameworks.
- Open Access
- 1 August 2025
- Published by Poltekkes Kemenkes Surabaya in Journal of Electronics, Electromedical Engineering, and Medical Informatics
- Vol. 7 (4) , 1028-1044
A Reproducible Workflow for Liver Volume Segmentation and 3D Model Generation Using Open-Source Tools
Complex liver resections related to hepatic tumors represent a major surgical challenge that requires precise preoperative planning supported by reliable three-dimensional (3D) anatomical models. In this context, accurate volumetric segmentation of the liver is a critical prerequisite to ensure the fidelity of printed models and to optimize surgical decision-making. This study compares different segmentation techniques integrated into open-source software to identify the most suitable approach for clinical application in resource-limited settings. Three semi-automatic methods, region growing, thresholding, and contour interpolation, were tested using the 3D Slicer platform and compared with a proprietary automatic method (Hepatic VCAR, GE Healthcare) and a manual segmentation reference, considered the gold standard. Ten anonymized abdominal CT volumes from the Medical Segmentation Decathlon dataset, encompassing various hepatic pathologies, were used to assess and compare the performance of each technique. Evaluation metrics included the Dice similarity coefficient (Dice), Hausdorff distance (HD), root mean square error (RMS), standard deviation (SD), and colorimetric surface discrepancy maps, enabling both quantitative and qualitative analysis of segmentation accuracy. Among the tested methods, the semi-automatic region growing approach demonstrated the highest agreement with manual segmentation (Dice = 0.935 ± 0.013; HD = 4.32 ± 0.48 mm), surpassing both other semi-automatic techniques and the automatic proprietary method. These results suggest that the region growing method implemented in 3D Slicer offers a reliable, accurate, and reproducible workflow for generating 3D liver models, particularly in surgical environments with limited access to advanced commercial solutions. The proposed methodology can potentially improve surgical planning, enhance training through realistic patient-specific models, and facilitate broader adoption of 3D printing in hepatobiliary surgery worldwide.
- 1 August 2025
- Published by Poltekkes Kemenkes Surabaya in Journal of Electronics, Electromedical Engineering, and Medical Informatics
- Vol. 7 (4) , 1028-1044
Open AccessA Reproducible Workflow for Liver Volume Segmentation and 3D Model Generation Using Open-Source Tools
Complex liver resections related to hepatic tumors represent a major surgical challenge that requires precise preoperative planning supported by reliable three-dimensional (3D) anatomical models. In this context, accurate volumetric segmentation of the liver is a critical prerequisite to ensure the fidelity of printed models and to optimize surgical decision-making. This study compares different segmentation techniques integrated into open-source software to identify the most suitable approach for clinical application in resource-limited settings. Three semi-automatic methods, region growing, thresholding, and contour interpolation, were tested using the 3D Slicer platform and compared with a proprietary automatic method (Hepatic VCAR, GE Healthcare) and a manual segmentation reference, considered the gold standard. Ten anonymized abdominal CT volumes from the Medical Segmentation Decathlon dataset, encompassing various hepatic pathologies, were used to assess and compare the performance of each technique. Evaluation metrics included the Dice similarity coefficient (Dice), Hausdorff distance (HD), root mean square error (RMS), standard deviation (SD), and colorimetric surface discrepancy maps, enabling both quantitative and qualitative analysis of segmentation accuracy. Among the tested methods, the semi-automatic region growing approach demonstrated the highest agreement with manual segmentation (Dice = 0.935 ± 0.013; HD = 4.32 ± 0.48 mm), surpassing both other semi-automatic techniques and the automatic proprietary method. These results suggest that the region growing method implemented in 3D Slicer offers a reliable, accurate, and reproducible workflow for generating 3D liver models, particularly in surgical environments with limited access to advanced commercial solutions. The proposed methodology can potentially improve surgical planning, enhance training through realistic patient-specific models, and facilitate broader adoption of 3D printing in hepatobiliary surgery worldwide.
- Open Access
- 1 June 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 15 (3) , 2616-2630
Particle swarm optimization tuned controllers for capacitor voltage balancing and harmonic suppression in modular multilevel converters
The modular multilevel converter (MMC) has become a highly attractive power converter topology for various applications due to its modularity and scalability. However, it faces significant challenges, such as capacitor voltage balancing and circulating current, which can lead to instability and high-power losses. While the sorting algorithm is commonly used to balance capacitor voltages, this paper uses an individual balancing control method as an alternative. Additionally, a proportional resonant controller is employed to suppress the second and fourth harmonics in the circulating current. This paper presents a method for tuning the parameters of both the circulating current controller and the individual balancing control using the particle swarm optimization (PSO) algorithm, which represents the main contribution of this work. The MMC system, connected to a grid with a low number of submodules, is modeled and evaluated using the PLECS and MATLAB/Simulink environments. The results demonstrate the effectiveness of the proposed PSO-based tuning method in improving the performance and stability of the MMC.
- 1 June 2025
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 15 (3) , 2616-2630
Open AccessParticle swarm optimization tuned controllers for capacitor voltage balancing and harmonic suppression in modular multilevel converters
The modular multilevel converter (MMC) has become a highly attractive power converter topology for various applications due to its modularity and scalability. However, it faces significant challenges, such as capacitor voltage balancing and circulating current, which can lead to instability and high-power losses. While the sorting algorithm is commonly used to balance capacitor voltages, this paper uses an individual balancing control method as an alternative. Additionally, a proportional resonant controller is employed to suppress the second and fourth harmonics in the circulating current. This paper presents a method for tuning the parameters of both the circulating current controller and the individual balancing control using the particle swarm optimization (PSO) algorithm, which represents the main contribution of this work. The MMC system, connected to a grid with a low number of submodules, is modeled and evaluated using the PLECS and MATLAB/Simulink environments. The results demonstrate the effectiveness of the proposed PSO-based tuning method in improving the performance and stability of the MMC.
- Open Access
- 1 September 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 15 (3) , 1490-1498
DSP implementation and discretization of phase locked loop methods in presence of grid imperfections
The fluctuation of grid variables affects the performance of the phase-locked loop, considerably reducing the efficiency of grid energy injection or compensation currents generation during active filtering. The phase locked loop is the main tool for grid synchronization, offering continuous, real-time extraction of grid variables. As these techniques are implemented on digital computers, their discretization and analysis of resource requirements is an important step. This work represents a discretization and implementation on a digital signal processing (DSP) board of two distinct phase-locked loop (PLL) techniques as well as a comparative study of the latter. Our study covers various aspects, including the discretization of the PLLs to be studied, an assessment of the hardware resources required, their implementation on a DSP board, and their effectiveness in quickly identifying grid variables in the presence of imbalance and harmonics, which represent the most frequent grid imperfections.
- 1 September 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 15 (3) , 1490-1498
Open AccessDSP implementation and discretization of phase locked loop methods in presence of grid imperfections
The fluctuation of grid variables affects the performance of the phase-locked loop, considerably reducing the efficiency of grid energy injection or compensation currents generation during active filtering. The phase locked loop is the main tool for grid synchronization, offering continuous, real-time extraction of grid variables. As these techniques are implemented on digital computers, their discretization and analysis of resource requirements is an important step. This work represents a discretization and implementation on a digital signal processing (DSP) board of two distinct phase-locked loop (PLL) techniques as well as a comparative study of the latter. Our study covers various aspects, including the discretization of the PLLs to be studied, an assessment of the hardware resources required, their implementation on a DSP board, and their effectiveness in quickly identifying grid variables in the presence of imbalance and harmonics, which represent the most frequent grid imperfections.
- Open Access
- 1 April 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 14 (2) , 1424-1436
Maximum power point tracking and space vector modulation control of quasi-z-source inverter for grid-connected photovoltaic systems
The quasi-Z-source inverter (qZSI) become one of the most promising power electronic converters for photovoltaic (PV) applications, due to its capability to perform a buck-boost conversion of the input voltage in a single stage. The control strategy based maximum power point tracking (MPPT) and proportional integral (PI) controller are well known in grid-connected with traditional configuration but not in qZSI. This paper presents a control strategy for qZSI grid-connected based on the MPPT algorithm and the linear control by PI controllers. This is complemented by the capability to efficiently transfer the harvested power to the grid, ensuring a unity power factor. The proposed control strategy effectively separates the control mechanisms for the direct current (DC) and alternating current (AC) sides by utilizing the two control variables, the shoot-through duty ratio and the modulation index. An adapted space vector modulation technique is then utilized to generate the switching pulse width modulation (PWM) signals, using these two control variables as inputs. The proposed approach was tested and validated under MATLAB/Simulink and PLECS software.
- 1 April 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 14 (2) , 1424-1436
Open AccessMaximum power point tracking and space vector modulation control of quasi-z-source inverter for grid-connected photovoltaic systems
The quasi-Z-source inverter (qZSI) become one of the most promising power electronic converters for photovoltaic (PV) applications, due to its capability to perform a buck-boost conversion of the input voltage in a single stage. The control strategy based maximum power point tracking (MPPT) and proportional integral (PI) controller are well known in grid-connected with traditional configuration but not in qZSI. This paper presents a control strategy for qZSI grid-connected based on the MPPT algorithm and the linear control by PI controllers. This is complemented by the capability to efficiently transfer the harvested power to the grid, ensuring a unity power factor. The proposed control strategy effectively separates the control mechanisms for the direct current (DC) and alternating current (AC) sides by utilizing the two control variables, the shoot-through duty ratio and the modulation index. An adapted space vector modulation technique is then utilized to generate the switching pulse width modulation (PWM) signals, using these two control variables as inputs. The proposed approach was tested and validated under MATLAB/Simulink and PLECS software.
- Open Access
- 20 March 2024
- Published by Oriental Scientific Publishing Company in Biomedical and Pharmacology Journal
- Vol. 17 (1) , 453-459
Assessing Heart Rate Variability and Pulse Rate Variability Patterns in Cardiac Patients: Exploring the Utility of Photoplethysmography and Electrocardiography
The measure of cardiac variability (HRV) is considered an accurate diagnostic method to identify autonomic dysfunction. The heart rate influences the pulse. Therefore, pulse rate variability (PRV), like HRV, precisely indicates autonomic nervous system tone. The research investigates the correlation between HRV for the ECG signal and PRV in a cardiac patient. Method and Materials: 53 electrocardiogram (ECG) and photoplethysmogram (PPG) signals for 8 minutes from the PhysioNet BIDMC PPG and Respiration Dataset were used. Afterward, the PRV from PPG and the R-R interval calculated independently using Acqknowledge software were used to estimate the ECG and get HRV characteristics. Results: According to the results, there was a strong correlation between the R-R interval for PRV (694.49 ± 112.98ms) and HRV (695.60 ± 112.97ms) (r=0.99). For all linear parameters for both domains, frequency and time of HRV and PRV, there was a significant positive correlation: HFnu (r =0.99), HF Power (r =1), LFnu (r = 0.99), LF Power (r = 1), RMSSD (r = 0.99), SDNN (r = 0.99), NN50 (r = 0.99), and pNN50 (r =0.99). The Bland & Altman plot demonstrated a high level of agreement among approaches for all parameters. Conclusion: According to the finding, which showed a high level of agreement because it provides values similar to PRV and HRV for all parameters, the idea of PRV rather than HRV can be used to assess sympathovagal regulation in a broad community-based investigation alongside HRV under various clinical circumstances.
- 20 March 2024
- Published by Oriental Scientific Publishing Company in Biomedical and Pharmacology Journal
- Vol. 17 (1) , 453-459
Open AccessAssessing Heart Rate Variability and Pulse Rate Variability Patterns in Cardiac Patients: Exploring the Utility of Photoplethysmography and Electrocardiography
The measure of cardiac variability (HRV) is considered an accurate diagnostic method to identify autonomic dysfunction. The heart rate influences the pulse. Therefore, pulse rate variability (PRV), like HRV, precisely indicates autonomic nervous system tone. The research investigates the correlation between HRV for the ECG signal and PRV in a cardiac patient. Method and Materials: 53 electrocardiogram (ECG) and photoplethysmogram (PPG) signals for 8 minutes from the PhysioNet BIDMC PPG and Respiration Dataset were used. Afterward, the PRV from PPG and the R-R interval calculated independently using Acqknowledge software were used to estimate the ECG and get HRV characteristics. Results: According to the results, there was a strong correlation between the R-R interval for PRV (694.49 ± 112.98ms) and HRV (695.60 ± 112.97ms) (r=0.99). For all linear parameters for both domains, frequency and time of HRV and PRV, there was a significant positive correlation: HFnu (r =0.99), HF Power (r =1), LFnu (r = 0.99), LF Power (r = 1), RMSSD (r = 0.99), SDNN (r = 0.99), NN50 (r = 0.99), and pNN50 (r =0.99). The Bland & Altman plot demonstrated a high level of agreement among approaches for all parameters. Conclusion: According to the finding, which showed a high level of agreement because it provides values similar to PRV and HRV for all parameters, the idea of PRV rather than HRV can be used to assess sympathovagal regulation in a broad community-based investigation alongside HRV under various clinical circumstances.
- 27 February 2024
- Published by Springer Nature
- p. 141-150
EEG-Based Drivers Drowsiness Prediction Using Personalized Features Extraction and Classification Methods Under Python
- 27 February 2024
- Published by Springer Nature
- p. 141-150
EEG-Based Drivers Drowsiness Prediction Using Personalized Features Extraction and Classification Methods Under Python