Eman Mounir Ali
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Eman Mounir Ali has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
M.E. Khalifa
2 shared publications- Mohamed Taha
Department of Computer Science, Faculty of Computers and Artificial intelligence, Benha University, Benha, Egypt
2 shared publications - R.M. Haggag2 shared publications
- Rasha Elstohy
Obour Inst, Dept Informat Syst, El Sharqia, Egypt
2 shared publications - Abdallah Donia
Department of Scientific Computing, Faculty of Computer and Artificial Intelligence, Benha University, Benha 13518, Egypt
1 shared publication - Ayat Taha1 shared publication
Latest Publications
- Open Access
- 24 November 2025
- Published by MDPI AG in Current Issues in Molecular Biology
- Vol. 47 (12) , 976
Comparative Multi-Omics Analysis Identifies Shared Transcriptomic Signatures and Therapeutic Targets in Alzheimer’s, Parkinson’s, and Huntington’s Diseases
Alzheimer’s disease (AD), Parkinson’s disease (PD), and Huntington’s disease (HD) are major neurodegenerative disorders that share certain pathological features but differ in their genetic etiology and clinical presentation. Their potential molecular intersections remain incompletely understood. In this research, we conducted a comparative transcriptomic analysis using postmortem brain RNA-seq datasets from AD (GSE53697), PD (GSE68719), and HD (GSE64810) to identify shared and disease-specific transcriptional signatures. Differentially expressed genes (DEGs) were determined and functionally characterized through Gene Ontology (GO) enrichment. Protein–protein interaction (PPI) networks were generated using STRING and visualized in Cytoscape to identify central hub genes, followed by gene–disease and drug-interaction analyses to assess functional and therapeutic relevance. Ten DEGs were found to overlap among the three disorders, exhibiting variable directions of regulation across diseases. Enrichment analysis indicated convergence on immune- and inflammation-related biological processes. Key hub genes, including MMP9, LCN2, CXCL2, CCL2, S100A8, and S100A9, were identified as central nodes within the PPI network. Although the overlap in DEGs was limited, the findings suggest that neuroinflammatory signaling represents a shared molecular theme across AD, PD, and HD, warranting further validation in independent cohorts.
- 24 November 2025
- Published by MDPI AG in Current Issues in Molecular Biology
- Vol. 47 (12) , 976
Open AccessComparative Multi-Omics Analysis Identifies Shared Transcriptomic Signatures and Therapeutic Targets in Alzheimer’s, Parkinson’s, and Huntington’s Diseases
Alzheimer’s disease (AD), Parkinson’s disease (PD), and Huntington’s disease (HD) are major neurodegenerative disorders that share certain pathological features but differ in their genetic etiology and clinical presentation. Their potential molecular intersections remain incompletely understood. In this research, we conducted a comparative transcriptomic analysis using postmortem brain RNA-seq datasets from AD (GSE53697), PD (GSE68719), and HD (GSE64810) to identify shared and disease-specific transcriptional signatures. Differentially expressed genes (DEGs) were determined and functionally characterized through Gene Ontology (GO) enrichment. Protein–protein interaction (PPI) networks were generated using STRING and visualized in Cytoscape to identify central hub genes, followed by gene–disease and drug-interaction analyses to assess functional and therapeutic relevance. Ten DEGs were found to overlap among the three disorders, exhibiting variable directions of regulation across diseases. Enrichment analysis indicated convergence on immune- and inflammation-related biological processes. Key hub genes, including MMP9, LCN2, CXCL2, CCL2, S100A8, and S100A9, were identified as central nodes within the PPI network. Although the overlap in DEGs was limited, the findings suggest that neuroinflammatory signaling represents a shared molecular theme across AD, PD, and HD, warranting further validation in independent cohorts.
- Open Access
- 24 May 2025
- Published by Elsevier in Egyptian Informatics Journal
- Vol. 30
Enhanced multiple sclerosis diagnosis by MRI image retrieval using convolutional autoencoders
- 24 May 2025
- Published by Elsevier in Egyptian Informatics Journal
- Vol. 30
Open AccessEnhanced multiple sclerosis diagnosis by MRI image retrieval using convolutional autoencoders
- Open Access
- 1 February 2025
- Published by Elsevier in Results in Control and Optimization
- Vol. 18
Multiple sclerosis diagnosis with brain MRI retrieval: A deep learning approach
- 1 February 2025
- Published by Elsevier in Results in Control and Optimization
- Vol. 18
Open AccessMultiple sclerosis diagnosis with brain MRI retrieval: A deep learning approach
- Open Access
- 1 January 2025
- Published by Wiley in Applied Computational Intelligence and Soft Computing
- Vol. 2025 (1)
Optimization of Hybrid Machine Learning Approach for Unemployment Rate Forecasting
This research proposes a robust approach for forecasting female unemployment rates across various regions in Egypt using optimized support vector machines (SVMs). Key factors such as education level, age, and location are analyzed to enhance prediction accuracy. The process involves three phases: training, predicting, and optimizing. Training data are derived from CAPMAS reports (2018–2023), which provide quarterly labor force assessments categorized by multiple factors. The SVM model was evaluated using linear, polynomial, and Gaussian kernels, with the polynomial kernel demonstrating superior accuracy and low error rates. To further improve predictions, optimization techniques—gray wolf optimizer (GWO), whale optimization algorithm (WOA), and moth‐flame optimization (MFO)—were applied. GWO emerged as the most effective, reducing mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) up to 3.8%, 1.9%, and 11.5% with slight 0.6% decrease for R ‐squared ( R 2 ) in the education sector, while WOA also exhibited significant improvements. These results underscore the potential of integrating advanced machine learning models with optimization techniques for accurate unemployment rate forecasting. The findings offer valuable insights for policymakers, labor economists, and researchers, supporting data‐driven decision‐making to address unemployment challenges.
- 1 January 2025
- Published by Wiley in Applied Computational Intelligence and Soft Computing
- Vol. 2025 (1)
Open AccessOptimization of Hybrid Machine Learning Approach for Unemployment Rate Forecasting
This research proposes a robust approach for forecasting female unemployment rates across various regions in Egypt using optimized support vector machines (SVMs). Key factors such as education level, age, and location are analyzed to enhance prediction accuracy. The process involves three phases: training, predicting, and optimizing. Training data are derived from CAPMAS reports (2018–2023), which provide quarterly labor force assessments categorized by multiple factors. The SVM model was evaluated using linear, polynomial, and Gaussian kernels, with the polynomial kernel demonstrating superior accuracy and low error rates. To further improve predictions, optimization techniques—gray wolf optimizer (GWO), whale optimization algorithm (WOA), and moth‐flame optimization (MFO)—were applied. GWO emerged as the most effective, reducing mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) up to 3.8%, 1.9%, and 11.5% with slight 0.6% decrease for R ‐squared ( R 2 ) in the education sector, while WOA also exhibited significant improvements. These results underscore the potential of integrating advanced machine learning models with optimization techniques for accurate unemployment rate forecasting. The findings offer valuable insights for policymakers, labor economists, and researchers, supporting data‐driven decision‐making to address unemployment challenges.
- Open Access
- 11 November 2024
- Published by PeerJ in PeerJ Computer Science
- Vol. 10, e2430
A comparative analysis of variants of machine learning and time series models in predicting women’s participation in the labor force
Labor force participation of Egyptian women has been a chronic economic problem in Egypt. Despite the improvement in the human capital front, whether on the education or health indicators, female labor force participation remains persistently low. This study proposes a hybrid machine-learning model that integrates principal component analysis (PCA) for feature extraction with various machine learning and time-series models to predict women’s employment in times of crisis. Various machine learning (ML) algorithms, such as support vector machine (SVM), neural network, K-nearest neighbor (KNN), linear regression, random forest, and AdaBoost, in addition to popular time series algorithms, including autoregressive integrated moving average (ARIMA) and vector autoregressive (VAR) models, have been applied to an actual dataset from the public sector. The manpower dataset considered gender from different regions, ages, and educational levels. The dataset was then trained, tested, and evaluated. For performance validation, forecasting accuracy metrics were constructed using mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), mean absolute percent error (MAPE), R-squared (R2), and cross-validated root mean squared error (CVRMSE). Another Dickey-Fuller test was performed to evaluate and compare the accuracy of the applied models, and the results showed that AdaBoost outperforms the other methods by an accuracy of 100%. Compared to alternative works, our findings demonstrate a comprehensive comparative analysis for predicting women’s participation in different regions during an economic crisis.
- 11 November 2024
- Published by PeerJ in PeerJ Computer Science
- Vol. 10, e2430
Open AccessA comparative analysis of variants of machine learning and time series models in predicting women’s participation in the labor force
Labor force participation of Egyptian women has been a chronic economic problem in Egypt. Despite the improvement in the human capital front, whether on the education or health indicators, female labor force participation remains persistently low. This study proposes a hybrid machine-learning model that integrates principal component analysis (PCA) for feature extraction with various machine learning and time-series models to predict women’s employment in times of crisis. Various machine learning (ML) algorithms, such as support vector machine (SVM), neural network, K-nearest neighbor (KNN), linear regression, random forest, and AdaBoost, in addition to popular time series algorithms, including autoregressive integrated moving average (ARIMA) and vector autoregressive (VAR) models, have been applied to an actual dataset from the public sector. The manpower dataset considered gender from different regions, ages, and educational levels. The dataset was then trained, tested, and evaluated. For performance validation, forecasting accuracy metrics were constructed using mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), mean absolute percent error (MAPE), R-squared (R2), and cross-validated root mean squared error (CVRMSE). Another Dickey-Fuller test was performed to evaluate and compare the accuracy of the applied models, and the results showed that AdaBoost outperforms the other methods by an accuracy of 100%. Compared to alternative works, our findings demonstrate a comprehensive comparative analysis for predicting women’s participation in different regions during an economic crisis.
- Open Access
- 22 August 2023
- Published by Elsevier in The Egyptian Journal of Remote Sensing and Space Sciences
- Vol. 26 (3) , 807-814
A flash flood detected area using classification-based image processing for sentinel-2 satellites data: A case study of Zafaraana Road at Red Sea
- 22 August 2023
- Published by Elsevier in The Egyptian Journal of Remote Sensing and Space Sciences
- Vol. 26 (3) , 807-814
Open AccessA flash flood detected area using classification-based image processing for sentinel-2 satellites data: A case study of Zafaraana Road at Red Sea