Mohamad O. Diab
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mohamad O. Diab has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Rami Alkhatib
Rafik Hariri University
3 shared publications - Afif Swaidan1 shared publication
Alaa Seif
Rafik Hariri University
1 shared publicationChristophe Corbier
1 shared publication- Christophe Corbier
Université de Lyon, UJM-Saint-Etienne, LASPI, IUT de Roanne
1 shared publication - Jad Al Soussi1 shared publication
Latest Publications
- Open Access
- 18 November 2026
- Published by MDPI AG in Preprints.org
Optimizing Deep Learning Pipelines for Retinopathy of Prematurity Classification: A Systematic Study from Preprocessing to Model Selection
Retinopathy of Prematurity (ROP) remains one of the leading causes of preventable childhood blindness, yet automated detection remains challenging due to variations in retinal fundus image quality, contrast, acquisition device characteristics, and disease representation, which proposes a deep learning pipeline for binary classification of healthy and ROP cases using the recently introduced ROPReLes dataset, which contains 6004 retinal images from188 subjects. To mitigate bias and prevent data leakage, a patient-wise data split was performed. Multiple preprocessing strategies were tested, including three normalization methods, contrast enhancement techniques (CLAHE & histogram equalization) and color-space transformations. Several data augmentation and class-balancing strategies were also evaluated, including weighted sampling, on-the-go augmentation, offline augmentation, and ratio-based augmentation. Performance was assessed using both baseline and state-of-the-art architectures, including a custom 2D convolutional neural network, ResNet18, Inception-v1, Inception-v3, EfficientNet, and Swin Transformer. The results show that model performance is strongly influenced by the combined effects of preprocessing, augmentation, class balancing, batch size, and model architecture. Ratio-based augmentation, applied only on the minority class, was the most effective class- balancing strategy. Among the evaluated models, Inception-v3 achieved the highest AUC (88.5%) and an accuracy of 91.3%. These findings highlight the importance of optimizing preprocessing, data balancing, and model selection as a unified pipeline for developing reliable automated ROP screening systems.
- 18 November 2026
- Published by MDPI AG in Preprints.org
Open AccessOptimizing Deep Learning Pipelines for Retinopathy of Prematurity Classification: A Systematic Study from Preprocessing to Model Selection
Retinopathy of Prematurity (ROP) remains one of the leading causes of preventable childhood blindness, yet automated detection remains challenging due to variations in retinal fundus image quality, contrast, acquisition device characteristics, and disease representation, which proposes a deep learning pipeline for binary classification of healthy and ROP cases using the recently introduced ROPReLes dataset, which contains 6004 retinal images from188 subjects. To mitigate bias and prevent data leakage, a patient-wise data split was performed. Multiple preprocessing strategies were tested, including three normalization methods, contrast enhancement techniques (CLAHE & histogram equalization) and color-space transformations. Several data augmentation and class-balancing strategies were also evaluated, including weighted sampling, on-the-go augmentation, offline augmentation, and ratio-based augmentation. Performance was assessed using both baseline and state-of-the-art architectures, including a custom 2D convolutional neural network, ResNet18, Inception-v1, Inception-v3, EfficientNet, and Swin Transformer. The results show that model performance is strongly influenced by the combined effects of preprocessing, augmentation, class balancing, batch size, and model architecture. Ratio-based augmentation, applied only on the minority class, was the most effective class- balancing strategy. Among the evaluated models, Inception-v3 achieved the highest AUC (88.5%) and an accuracy of 91.3%. These findings highlight the importance of optimizing preprocessing, data balancing, and model selection as a unified pipeline for developing reliable automated ROP screening systems.
- Open Access
- 16 July 2021
- Published by ASME International
Artificial Neural Network Based on Ensemble Empirical Mode Decomposition Features for Human Gait Diagnosis and Classification
Gait, which is the scientific term for walking, is one of the most important activities of daily life for humans. Gait performance is used as a general measure of functional ability, health, and well-being of individuals. Gait analysis using kinetic data such as pressure distribution underneath the foot has been a topic of interest for assessing falls in elderly and certain
- 16 July 2021
- Published by ASME International
Open AccessArtificial Neural Network Based on Ensemble Empirical Mode Decomposition Features for Human Gait Diagnosis and Classification
Gait, which is the scientific term for walking, is one of the most important activities of daily life for humans. Gait performance is used as a general measure of functional ability, health, and well-being of individuals. Gait analysis using kinetic data such as pressure distribution underneath the foot has been a topic of interest for assessing falls in elderly and certain
- Open Access
- 16 July 2021
- Published by ASME International
Design of Robotic Manipulator to Hollow Out Zucchini
Robots are programmable machines that can perform complex tasks in different domains while guaranteeing cleanliness, improving safety, and saving time and products. Interestingly, one of the domains is the food industry and more specifically the Middle Eastern kitchen. Stuffed Zucchini is a very important dish whose ultimate challenge is to avoid poking its bottom with the corer.
- 16 July 2021
- Published by ASME International
Open AccessDesign of Robotic Manipulator to Hollow Out Zucchini
Robots are programmable machines that can perform complex tasks in different domains while guaranteeing cleanliness, improving safety, and saving time and products. Interestingly, one of the domains is the food industry and more specifically the Middle Eastern kitchen. Stuffed Zucchini is a very important dish whose ultimate challenge is to avoid poking its bottom with the corer.
- 18 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 4 (6) , 1-4
Machine Learning Algorithm for Gait Analysis and Classification on Early Detection of Parkinson
Gait analysis using kinetic data such as pressure distribution underneath the foot has been a topic of interest for assessing falls in elderly and certain pathology such as Parkinson's disease. The disease which affects the central nervous system, cannot be ultimately diagnosed by a test. In this paper, we describe a detection algorithm able to classify subjects into Parkinson or normal subjects based on load distribution during gait. This will allow those with the disease to benefit from early detection and thus early treatment. We perform spatial and time signal analysis over vertical ground reaction forces (VGRFs), to categorize gaits as balanced or unbalanced. Where unbalanced gaits correspond to subjects with Parkinson Disease, and balanced gaits could be relevant to both normal or diseased subjects. Then simple features like correlation are used to further differentiate between balanced-normal subjects and balanced-diseased subjects.
- 18 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 4 (6) , 1-4
Machine Learning Algorithm for Gait Analysis and Classification on Early Detection of Parkinson
Gait analysis using kinetic data such as pressure distribution underneath the foot has been a topic of interest for assessing falls in elderly and certain pathology such as Parkinson's disease. The disease which affects the central nervous system, cannot be ultimately diagnosed by a test. In this paper, we describe a detection algorithm able to classify subjects into Parkinson or normal subjects based on load distribution during gait. This will allow those with the disease to benefit from early detection and thus early treatment. We perform spatial and time signal analysis over vertical ground reaction forces (VGRFs), to categorize gaits as balanced or unbalanced. Where unbalanced gaits correspond to subjects with Parkinson Disease, and balanced gaits could be relevant to both normal or diseased subjects. Then simple features like correlation are used to further differentiate between balanced-normal subjects and balanced-diseased subjects.
- 13 October 2019
- Published by Springer Nature
- p. 17-44
A Review on ECG-Based Biometric Authentication Systems
- 13 October 2019
- Published by Springer Nature
- p. 17-44
A Review on ECG-Based Biometric Authentication Systems