Oussama El Gannour
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Oussama El Gannour has a total of 52 co-authors. Here are the top co-authors by number of shared publications:
- Bouchaib Cherradi
Hassan II University of Casablanca
30 shared publications Soufiane Hamida
18 shared publicationsAbdelhadi Raihani
EN SET of Mohammedia, Hassan II University of Casablanca,EElS Laboratory,Mohammedia,Morocco
12 shared publications- Soufiane Hamida
Hassan II University of Casablanca
9 shared publications - Abdelhadi Raihani
Hassan II University of Casablanca
6 shared publications Hassan Ouajji
Electrical Engineering and Intelligent Systems (EEIS) Laboratory, ENSET of Mohammedia, Hassan II University of Casablanca, Mohammedia, Morocco
5 shared publications
Latest Publications
- Open Access
- 19 December 2025
- Published by Elsevier in Scientific African
- Vol. 31
A novel spatially enabled neural model for flood susceptibility in Northern Morocco
- 19 December 2025
- Published by Elsevier in Scientific African
- Vol. 31
Open AccessA novel spatially enabled neural model for flood susceptibility in Northern Morocco
- Open Access
- 19 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 145977-145995
Real-Time Adaptive Target Tracking via Inverse Kinematics Optimization in Stabilized Systems
To keep a target item inside their field of view, two-axis gimbal systems are designed to dynamically compensate for any movements that may occur, whether such movements originate from the target itself or from the platform on which the device is mounted. This study addresses the development and optimization of inverse kinematics algorithms to enable precise, real-time target tracking in Inertial Stabilization Platforms (ISPs), also known as gimbal systems. These systems are critical for applications demanding high stability and accuracy, such as surveillance, navigation, and scientific research. The research begins with a thorough exploration of the mathematical principles governing inverse kinematics, emphasizing the complexities introduced by real-time processing constraints. To overcome these challenges, advanced optimization techniques are applied, focusing on minimizing computational delays and enhancing tracking precision. The proposed algorithms are implemented within a Simscape Multibody simulation framework, allowing for rigorous testing under diverse operational conditions. The validation process combines simulated environments with real-world experiments to ensure the algorithms’ robustness and practical utility. The findings reveal notable advancements in both tracking accuracy and system responsiveness, offering a pathway to more efficient and dependable gimbal systems in highly dynamic settings.
- 19 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 145977-145995
Open AccessReal-Time Adaptive Target Tracking via Inverse Kinematics Optimization in Stabilized Systems
To keep a target item inside their field of view, two-axis gimbal systems are designed to dynamically compensate for any movements that may occur, whether such movements originate from the target itself or from the platform on which the device is mounted. This study addresses the development and optimization of inverse kinematics algorithms to enable precise, real-time target tracking in Inertial Stabilization Platforms (ISPs), also known as gimbal systems. These systems are critical for applications demanding high stability and accuracy, such as surveillance, navigation, and scientific research. The research begins with a thorough exploration of the mathematical principles governing inverse kinematics, emphasizing the complexities introduced by real-time processing constraints. To overcome these challenges, advanced optimization techniques are applied, focusing on minimizing computational delays and enhancing tracking precision. The proposed algorithms are implemented within a Simscape Multibody simulation framework, allowing for rigorous testing under diverse operational conditions. The validation process combines simulated environments with real-world experiments to ensure the algorithms’ robustness and practical utility. The findings reveal notable advancements in both tracking accuracy and system responsiveness, offering a pathway to more efficient and dependable gimbal systems in highly dynamic settings.
- Open Access
- 10 January 2025
- Published by Mesopotamian Academic Press - DIGITAL COMMONS JOURNALS in Mesopotamian Journal of CyberSecurity
- Vol. 5 (1) , 187-201
Internet of Things for Smart Building Security: Leveraging a Blockchain for Enhanced IoT Security
This literature review looks at the transformative impact of Internet of Things (IoT) technology on smart building management systems with a focus on enhancing operational efficiency, occupant safety, and comfort. As the number of IoT applications in the built environment increases, technology breakthroughs simplify and automate critical functions, including energy management, security, and environmental control. Despite all the advantages, such as the integration of the IoT with smart buildings, there are barriers, such as the compatibility of systems, scalability of infrastructure and data security and privacy issues in a connected ecosystem. This review examines some of those barriers and outlines potential solutions, such as standardized communication protocols, improved cybersecurity, and scalable, cost-effective IoT frameworks for existing and new buildings. The aim of the findings is to guide building owners, stakeholders, architects and urban planners in maximizing the benefits of IoT technology to create smarter, more sustainable and responsive buildings that support urban sustainability and foster better quality of life for tenants.
- 10 January 2025
- Published by Mesopotamian Academic Press - DIGITAL COMMONS JOURNALS in Mesopotamian Journal of CyberSecurity
- Vol. 5 (1) , 187-201
Open AccessInternet of Things for Smart Building Security: Leveraging a Blockchain for Enhanced IoT Security
This literature review looks at the transformative impact of Internet of Things (IoT) technology on smart building management systems with a focus on enhancing operational efficiency, occupant safety, and comfort. As the number of IoT applications in the built environment increases, technology breakthroughs simplify and automate critical functions, including energy management, security, and environmental control. Despite all the advantages, such as the integration of the IoT with smart buildings, there are barriers, such as the compatibility of systems, scalability of infrastructure and data security and privacy issues in a connected ecosystem. This review examines some of those barriers and outlines potential solutions, such as standardized communication protocols, improved cybersecurity, and scalable, cost-effective IoT frameworks for existing and new buildings. The aim of the findings is to guide building owners, stakeholders, architects and urban planners in maximizing the benefits of IoT technology to create smarter, more sustainable and responsive buildings that support urban sustainability and foster better quality of life for tenants.
- Open Access
- 14 February 2024
- Published by International Association of Online Engineering (IAOE) in International Journal of Online and Biomedical Engineering (iJOE)
- Vol. 20 (02) , 78-94
An Integrated Multimodal Deep Learning Framework for Accurate Skin Disease Classification
In order to effectively treat skin diseases, an accurate and prompt diagnosis is required. In this article, a novel method for classifying skin disorders using a multimodal classifier is presented. The proposed classifier utilizes multiple information sources to enhance the accuracy of disease classification. It incorporates images of skin lesions and patient-specific data. The multimodal classifier simultaneously classifies diseases by combining image and structured data inputs. The effectiveness of the proposed classifier was evaluated using the ISIC 2018 dataset, which includes images and clinical data for seven categories of skin diseases. The results indicate that the proposed model outperforms conventional single-modal and single-task classifiers, achieving an accuracy of 98.66% for image classification and 94.40% for clinical data classification. In addition, we compare the performance of the proposed model with that of other methodologies, demonstrating its superiority. Despite yielding promising results, the proposed method has limitations in terms of data requirements and generalizability. Future research directions include incorporating additional information sources, investigating genetic data integration, and applying the method to various medical conditions. This study illustrates the potential of integrating multimodal techniques with transfer learning in deep neural networks to enhance the classification accuracy of cutaneous diseases.
- 14 February 2024
- Published by International Association of Online Engineering (IAOE) in International Journal of Online and Biomedical Engineering (iJOE)
- Vol. 20 (02) , 78-94
Open AccessAn Integrated Multimodal Deep Learning Framework for Accurate Skin Disease Classification
In order to effectively treat skin diseases, an accurate and prompt diagnosis is required. In this article, a novel method for classifying skin disorders using a multimodal classifier is presented. The proposed classifier utilizes multiple information sources to enhance the accuracy of disease classification. It incorporates images of skin lesions and patient-specific data. The multimodal classifier simultaneously classifies diseases by combining image and structured data inputs. The effectiveness of the proposed classifier was evaluated using the ISIC 2018 dataset, which includes images and clinical data for seven categories of skin diseases. The results indicate that the proposed model outperforms conventional single-modal and single-task classifiers, achieving an accuracy of 98.66% for image classification and 94.40% for clinical data classification. In addition, we compare the performance of the proposed model with that of other methodologies, demonstrating its superiority. Despite yielding promising results, the proposed method has limitations in terms of data requirements and generalizability. Future research directions include incorporating additional information sources, investigating genetic data integration, and applying the method to various medical conditions. This study illustrates the potential of integrating multimodal techniques with transfer learning in deep neural networks to enhance the classification accuracy of cutaneous diseases.
- Open Access
- 1 February 2024
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 13 (1) , 628-637
Improving skin diseases prediction through data balancing via classes weighting and transfer learning
Skin disease prediction using artificial intelligence has shown great potential in improving early diagnosis and treatment outcomes. However, the presence of class imbalance within skin disease datasets poses a significant challenge for accurate prediction, particularly for rare diseases. This study proposes a novel approach to address class imbalance through data balancing using classes weighting, coupled with transfer learning techniques, to enhance the performance of skin disease prediction models. Two experiments were conducted using a tuned EfficientNetV2L based classifier. In the first experiment, a default dataset structure was utilized for training and testing. The second experiment involved employing classes weighting approach to balance the dataset. The effectiveness of the proposed approach is evaluated using the ISIC 2018 dataset, which comprises a diverse collection of skin lesion images. By assigning appropriate weights to different classes based on their prevalence, the proposed method aims to balance the representation of rare disease classes. To evaluate the performance of the proposed methodology, several performance evaluation metrics, including accuracy, precision, and recall, were employed. These findings revealed that the balanced dataset achieved enhanced generalization, mitigating the biases associated with class imbalance. As a result, the efficacy of artificial intelligence models is enhanced.
- 1 February 2024
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 13 (1) , 628-637
Open AccessImproving skin diseases prediction through data balancing via classes weighting and transfer learning
Skin disease prediction using artificial intelligence has shown great potential in improving early diagnosis and treatment outcomes. However, the presence of class imbalance within skin disease datasets poses a significant challenge for accurate prediction, particularly for rare diseases. This study proposes a novel approach to address class imbalance through data balancing using classes weighting, coupled with transfer learning techniques, to enhance the performance of skin disease prediction models. Two experiments were conducted using a tuned EfficientNetV2L based classifier. In the first experiment, a default dataset structure was utilized for training and testing. The second experiment involved employing classes weighting approach to balance the dataset. The effectiveness of the proposed approach is evaluated using the ISIC 2018 dataset, which comprises a diverse collection of skin lesion images. By assigning appropriate weights to different classes based on their prevalence, the proposed method aims to balance the representation of rare disease classes. To evaluate the performance of the proposed methodology, several performance evaluation metrics, including accuracy, precision, and recall, were employed. These findings revealed that the balanced dataset achieved enhanced generalization, mitigating the biases associated with class imbalance. As a result, the efficacy of artificial intelligence models is enhanced.
- Open Access
- 1 February 2024
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 13 (1) , 538-547
Toward enhanced skin disease classification using a hybrid RF-DNN system leveraging data balancing and augmentation techniques
Significant health concerns are associated with skin diseases, and accurate and timely diagnosis is essential for effective treatment and patient management. To improve the classification of cutaneous diseases, we propose a novel hybrid system that incorporates the strengths of random forest (RF) and deep neural network (DNN) algorithms. The system employs data augmentation and balancing techniques to enhance model performance and generalizability. The HAM10000 dataset of diverse dermatoscopic images is used for training and evaluation in this study. In the hybrid system proposed, the RF model provides an initial diagnosis based on patient-reported symptoms, while the DNN analyzes images of skin lesions, resulting in more precise and efficient diagnoses. Using hyper-parameter optimization, we fine-tune the system for optimal performance. The evaluation demonstrates the accuracy of the hybrid model, which achieves a classification accuracy of 96.8% overall. According to our findings, the hybrid system demonstrates exceptional efficacy in six of seven skin disease classes. Variations in sensitivity and reliance on data quality and quantity are however cited as limitations. Nevertheless, this hybrid system has the potential to revolutionize skin disease diagnosis and treatment.
- 1 February 2024
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 13 (1) , 538-547
Open AccessToward enhanced skin disease classification using a hybrid RF-DNN system leveraging data balancing and augmentation techniques
Significant health concerns are associated with skin diseases, and accurate and timely diagnosis is essential for effective treatment and patient management. To improve the classification of cutaneous diseases, we propose a novel hybrid system that incorporates the strengths of random forest (RF) and deep neural network (DNN) algorithms. The system employs data augmentation and balancing techniques to enhance model performance and generalizability. The HAM10000 dataset of diverse dermatoscopic images is used for training and evaluation in this study. In the hybrid system proposed, the RF model provides an initial diagnosis based on patient-reported symptoms, while the DNN analyzes images of skin lesions, resulting in more precise and efficient diagnoses. Using hyper-parameter optimization, we fine-tune the system for optimal performance. The evaluation demonstrates the accuracy of the hybrid model, which achieves a classification accuracy of 96.8% overall. According to our findings, the hybrid system demonstrates exceptional efficacy in six of seven skin disease classes. Variations in sensitivity and reliance on data quality and quantity are however cited as limitations. Nevertheless, this hybrid system has the potential to revolutionize skin disease diagnosis and treatment.
- Open Access
- 25 October 2023
- Published by International Association of Online Engineering (IAOE) in International Journal of Online and Biomedical Engineering (iJOE)
- Vol. 19 (15) , 61-76
Optimizing Machine Learning Algorithms for Heart Disease Classification and Prediction
According to the World Health Organization (WHO), cardiovascular disease is one of the leading causes of death worldwide. Thus, the prevention of this kind of illness is considered as a huge human health challenge. Additionally, the diagnostic process often involves a combination of clinical examination, laboratory tests, and other diagnostic procedures, which can be complex and time-consuming. However, advances in medical technology and research have led to improved methods for diagnosing heart disease, which can help to improve patient outcomes. Furthermore, Machine Learning (ML) methods have shown promise in helping to improve the diagnosis of heart disease. Each method requires specific parameters to produce good results. In this paper, we propose a diagnosis support system based on optimized Machine Learning algorithms, which is Artificial Neural Network (ANN), Support Vector Machine (SVM), K_Nearest Neighbour (KNN), Naive Bayes (NB), and Decision Tree (DT) to analyze the major cardiovascular risk factors, such as age, gender, high blood pressure, etc. To train and validate the ML models, a medical dataset of 558 patients with atherosclerosis is used. In this work, we achieved a 96.67% as promising accuracy level for the atherosclerosis prediction with ANN.
- 25 October 2023
- Published by International Association of Online Engineering (IAOE) in International Journal of Online and Biomedical Engineering (iJOE)
- Vol. 19 (15) , 61-76
Open AccessOptimizing Machine Learning Algorithms for Heart Disease Classification and Prediction
According to the World Health Organization (WHO), cardiovascular disease is one of the leading causes of death worldwide. Thus, the prevention of this kind of illness is considered as a huge human health challenge. Additionally, the diagnostic process often involves a combination of clinical examination, laboratory tests, and other diagnostic procedures, which can be complex and time-consuming. However, advances in medical technology and research have led to improved methods for diagnosing heart disease, which can help to improve patient outcomes. Furthermore, Machine Learning (ML) methods have shown promise in helping to improve the diagnosis of heart disease. Each method requires specific parameters to produce good results. In this paper, we propose a diagnosis support system based on optimized Machine Learning algorithms, which is Artificial Neural Network (ANN), Support Vector Machine (SVM), K_Nearest Neighbour (KNN), Naive Bayes (NB), and Decision Tree (DT) to analyze the major cardiovascular risk factors, such as age, gender, high blood pressure, etc. To train and validate the ML models, a medical dataset of 558 patients with atherosclerosis is used. In this work, we achieved a 96.67% as promising accuracy level for the atherosclerosis prediction with ANN.
- Top Cited Papers
- 15 September 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (11) , 33207-33234
Predicting patients with Parkinson's disease using Machine Learning and ensemble voting technique
- 15 September 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (11) , 33207-33234
Top Cited PapersPredicting patients with Parkinson's disease using Machine Learning and ensemble voting technique
- Open Access
- 24 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Classifying Brain Tumors using Convolutional Neural Networks on MRI Scans
Brain tumors are a significant cause of morbidity and mortality worldwide, with a high demand for accurate and robust diagnosis. The brain classification tumors using convolutional neural networks are a rapidly growing field in medical imaging. Brain tumors are a serious condition that can cause significant morbidity and mortality. Deep neural networks have been used in recent years to identify and classify images, with good results in areas such as medical image analysis. This work aims to use deep learning methods and CNNs to identify brain tumors in magnetic resonance imaging scans. Our work is motivated by the challenges that physicians face when trying to recognize brain tumors, particularly in the early stages, when mistakes can be made. Through various MRI experiments, we developed and evaluated two pre-trained convolutional neural networks which are InceptionV3 and ResNet50. Normal, Glioma, Meningioma, and Pituitary are the four distinct classes of brain images categorized by these models. The ResNet50 model was able to classify brain tumors using MRI scans with an overall accuracy of 96%.
- 24 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessClassifying Brain Tumors using Convolutional Neural Networks on MRI Scans
Brain tumors are a significant cause of morbidity and mortality worldwide, with a high demand for accurate and robust diagnosis. The brain classification tumors using convolutional neural networks are a rapidly growing field in medical imaging. Brain tumors are a serious condition that can cause significant morbidity and mortality. Deep neural networks have been used in recent years to identify and classify images, with good results in areas such as medical image analysis. This work aims to use deep learning methods and CNNs to identify brain tumors in magnetic resonance imaging scans. Our work is motivated by the challenges that physicians face when trying to recognize brain tumors, particularly in the early stages, when mistakes can be made. Through various MRI experiments, we developed and evaluated two pre-trained convolutional neural networks which are InceptionV3 and ResNet50. Normal, Glioma, Meningioma, and Pituitary are the four distinct classes of brain images categorized by these models. The ResNet50 model was able to classify brain tumors using MRI scans with an overall accuracy of 96%.
- 18 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Healthcare Embedded System for Predicting Parkinson's Disease Based on AI of Things
This study aims to build a healthcare-embedded system based on the Artificial Intelligence of Things (AIoT) to predict people affected by Parkinson's Disease (PD) via vocal disorders either locally or remotely. This system has been created based on several techniques of artificial intelligence such as dataset analysis, selection of classifiers and searching for the optimal hyperparameters that provide good performance without affecting the classifier's performance and the speed of classification. Also., this system is designed to be able to record audio, analyze sound signals and extract features based on several signal analysis libraries and artificial intelligence algorithms. We employed many intermediate libraries between the system, servers and the user to facilitate utilization of the system, to make it able to work anytime and anywhere in the world and to provide insight into the contribution of embedded systems based on AIoT for enhancing the quality of medical services. Furthermore, performance evaluation techniques have been used to estimate the accuracy., sensitivity., precision and area under the curve for several classifiers, and we selected the best classifiers to create an ensemble voting classifier that is the Kernel of our embedded system and it has an accuracy of 95.3%.
- 18 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Healthcare Embedded System for Predicting Parkinson's Disease Based on AI of Things
This study aims to build a healthcare-embedded system based on the Artificial Intelligence of Things (AIoT) to predict people affected by Parkinson's Disease (PD) via vocal disorders either locally or remotely. This system has been created based on several techniques of artificial intelligence such as dataset analysis, selection of classifiers and searching for the optimal hyperparameters that provide good performance without affecting the classifier's performance and the speed of classification. Also., this system is designed to be able to record audio, analyze sound signals and extract features based on several signal analysis libraries and artificial intelligence algorithms. We employed many intermediate libraries between the system, servers and the user to facilitate utilization of the system, to make it able to work anytime and anywhere in the world and to provide insight into the contribution of embedded systems based on AIoT for enhancing the quality of medical services. Furthermore, performance evaluation techniques have been used to estimate the accuracy., sensitivity., precision and area under the curve for several classifiers, and we selected the best classifiers to create an ensemble voting classifier that is the Kernel of our embedded system and it has an accuracy of 95.3%.