Mohamed Abdelfattah

Mohamed Abdelfattah

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2024 in Journal of Artificial Intelligence and Metaheuristics
Verified
Journal Article
Closed access
PDF file
AAAdmin Admin
Admin Admin
MAMohamed Abdelfattah
Mohamed Abdelfattah
IIIslam Ismail
Islam Ismail
El-Sayed M. El-KenawyEl-Sayed M. El-Kenawy
El-Sayed M. El-Kenawy
HMHossam El-Din Moustafa
Hossam El-Din Moustafa
MYMona Ahmed Yassen
Mona Ahmed Yassen
Accurate generation forecasting of Renewable Energy Sources (RES) is becoming more and more crucial for effective grid operation and energy management as RES are incorporated into the electrical grid. Because Machine Learning (ML) and Deep Learning (DL) algorithms can learn complicated relationships from data and provide accurate forecasts, they have become more popular than traditional forecasting approaches, which have limits. This article examines the state of the art and future directions in the field of ML and DL-based forecasting of renewable energy generation. This paper reviews the several approaches and models that have been used to project renewable energy. It also highlights the challenges, such as managing the uncertainty and unpredictability of renewable energy output, data accessibility, and model interpret ability. To sum up, this study emphasizes how important it is to develop accurate and dependable renewable energy forecasting models to facilitate the future transition to sustainable energy sources and enable the integration of RES into the electrical grid.

13 December 2023 in Optical and Quantum Electronics
Verified
Journal Article
Open access
PDF file
MAMohamed Abdelfattah
Mohamed Abdelfattah
SHSalem F. Hegazy
Salem F. Hegazy
SOS. S. A. Obayya
S. S. A. Obayya
Essential Secret Image Sharing (ESIS) decomposes a secret image into a set of shares that are distributed among categorized participants, and ensures that only authorized subsets of these participants can restore the image. All ESIS schemes to date have been based merely on computational techniques. In this paper, an optical ESIS system is introduced which uses unequal modulus decomposition (UMD) and optical gyrator transform (GT), offering high-speed parallel processing and dispensing with any pre-processing stages. The presented (1, 2, n) ESIS system generates n shares, including one essential share, such that any two shares that include the essential one, can reconstruct the initial secret image with no distortion. Any other unauthorized subset will not gain any information about the image. The scheme generates essential and nonessential shares that are of equal size, eliminating the need to concatenate sub-shares during the reconstruction of the secret image. The results verify that the secret image was completely retrieved in cases of authorized access, while full distortion occurred in cases of unauthorized access. The GT rotation angle serves as an additional authentication factor to validate the essential share and bolster the security. The optical ESIS system exhibits a high level of sensitivity to the changes in the GT rotation angle - that a variation of just 0.001 radians can cause the correlation coefficient to drop below 0.05.

6 March 2025 in International Journal of Telecommunications
Verified
Journal Article
Open access
PDF file
MSMoataz Mohamed El Sherbiny
Moataz Mohamed El Sherbiny
MAMohamed Abdelfattah
Mohamed Abdelfattah
ARAsmaa Hamdy Rabie
Asmaa Hamdy Rabie
AEAli Elsherbiny Taki Eldin
Ali Elsherbiny Taki Eldin
HMHossam El-Din Moustafa
Hossam El-Din Moustafa
It is no doubt that diabetes is considered one of the most common chronic diseases. Diabetes patients have high risk of diseases like renal failure, heart stroke, nerve and eye damage that can lead to blindness. Detection and prediction of diabetes mellitus is not a very easy process. Nevertheless, the cost of tests is high. Hospitals being busy therefore it could be a revolutionary if one could know the risk of being diabetic with no need to visit hospitals. This could only be done through artificial intelligence. In this paper, a classification model was proposed for diabetes mellitus classification and pre-diction, so that early diagnosis as well as treatment could prolong patients’ lives and minimize risk factors. The classification of datasets in medical healthcare is hindered by the problem of having suitable datasets. Proper processing was performed through null values imputation, normalization and encoding. Supervised algorithms were applied to ensure the effectiveness of the proposed model such as Random Forest (RF), Extreme Gradient Boosting (XGB) and Neural Network (NN). Results were compared using five performance metrics; accuracy, precision, f1-score, recall and run time. Training and testing are performed on two datasets. Results demonstrated that RF has overtaken both remaining techniques by achieving 80.5% accuracy compared to 79.65% for XGB and 76.36% for NN on the first dataset. While the second dataset results indicated RF superiority among remaining models by achieving an accuracy of 97.11% compared to 93.38% and 93.26 for NN and XGB respectively.

13 October 2024 in Journal of Artificial Intelligence in Engineering Practice
Verified
Journal Article
Open access
PDF file
AEAhmed Eslam
Ahmed Eslam
MAMohamed Abdelfattah
Mohamed Abdelfattah
El-Sayed M. El-KenawyEl-Sayed M. El-Kenawy
El-Sayed M. El-Kenawy
HMHossam El-Din Moustafa
Hossam El-Din Moustafa
Monkeypox is an illness like smallpox that began to spread through several countries at a relatively rapid pace. The rash is among monkeypox's most outstanding clinical features; however, a similar rash is evident in measles and chickenpox patients as well. AI and computer vision are well on their way to becoming must-have medical tools. For instance, computer-aided design (CAD) uses visual data to diagnose diseases such as chickenpox and measles at their early stage. Proposing a similar utilization of the AlexNet pre-trained model in extracting the differential features from MSID, the research has recorded an impressive precision rate of 0.932295, a testament to the credibility and precision of our research. We apply feature selection to reduce the extracted features in our proposed binary Greylag Goose Optimization (bGGO) method, a novel approach that we believe has the potential to significantly outperform existing models. It gives a better average fitness of 0.60068 and fixed best fitness as 0.50248. The presented model, with its novel approach, is discussed with several other optimization models, namely, binary waterwheel plant algorithm (bWWPA), Boosted Dipper Throated Optimization (bDTO), binary particle swarm optimizer (bPSO), binary whale optimization algorithm (bWAO), binary gray wolf optimizer (bGWO), and binary firefly algorithm (bFA). For the possibility of a difference between the subjects in the suggested approach and other methods, the results were subjected to the Wilcoxon signed-rank test and Analysis of variance. This comparison supported the novelty of this proposed method for the identification of monkeypox, sparking interest in its unique approach.

14 February 2025 in Optical and Quantum Electronics
Verified
Journal Article
Closed access
PDF file
MAMohamed Abdelfattah
Mohamed Abdelfattah
SHSalem F. Hegazy
Salem F. Hegazy
SOS. S. A. Obayya
S. S. A. Obayya

1 January 2025
Verified
Journal Article
Closed access
PDF file
MMMona Mona
Mona Mona
El-Sayed M. El-KenawyEl-Sayed M. El-Kenawy
El-Sayed M. El-Kenawy
MAMohamed Abdelfattah
Mohamed Abdelfattah
IIIslam Ismael
Islam Ismael
HMHossam El.DEen Salah Mostafa
Hossam El.DEen Salah Mostafa
MYMona Ahmed Yassen
Mona Ahmed Yassen
Wind energy is one of the fastest-growing sustainable, clean, and renewable sources, attracting significant attention and investment from many countries. However, given the substantial capital investment required for wind power plants, understanding the proposed plants’ performance becomes critical before implementation. This assessment is most effectively conducted using refined wind power predictability models and precise wind velocity data. Accurate wind forecasts are essential for informed decision-making and effective wind energy utilization. In this study, three advanced Machine Learning (ML) regression methods were applied to the TNWind dataset to predict the power output of wind turbines. The dataset variables included date and time (measured at 10-minute intervals), low-voltage active power (in kW), wind speed (in ms), the theoretical wind power curve (in kWh), and wind direction. To predict wind power output, six supervised ML models were trained, including Random Forest Regressor (RF), Extreme Gradient Boosting Regressor (XGB), Gradient Boosting Regressor (GB), Support Vector Machine Regressor (SVR), K-Neighbors Regressor (KN), and Linear Regressor. The analysis revealed that the Random Forest model outperformed the others, achieving exceptional performance metrics: an R2 value of 0.97, an MAE of 0.17 and an MSE of 0.07. The analysis to identify the outcomes for wind power generation from machine learning proves that renewable energies are more capable and are a lucrative investment.