Nariman A. Khaliel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nariman A. Khaliel has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Mohamed Eassa
Computer Science Department, Faculty of Information Systems and Computer Science, October 6 University, Giza 12585, Egypt
3 shared publications - Mohamed Elkholy
Faculty of Computer Science & Engineering, Alamein International University, Egypt
2 shared publications - Abdelrahman Hassan1 shared publication
Admin Admin
1 shared publication- Ahmed Elsharkawy
Faculty of Information Systems and Computer Science, October 6th University, Cairo, 12585, Egypt
1 shared publication - Alber S. Aziz
Faculty of Information, Systems and Computer Science, October 6th University, Cairo, 12585, Egypt
1 shared publication
Latest Publications
- Open Access
- 24 March 2026
- Published by Sciences Force in SciNexuses
- Vol. 3, 14-24
Investigating the Stability of a Perturbed Figure-8 Four-Body System Using Symplectic Integration
The figure-8 choreography of the equal-mass three-body problem is a rare example of a symmetric periodic solution in Newtonian gravity. In this study, we investigate the robustness of this orbit under a controlled perturbation: introducing a fourth body with variable mass and initial velocity while preserving the authorized figure-8 initial conditions for the original three bodies. We integrate the planar four-body equations of motion using a second-order symplectic leapfrog (velocity-Verlet) method to reduce long-term numerical drift in conserved quantities. Stability is quantified through a stability time defined by (i) a minimum pairwise-distance threshold to detect close encounters and (ii) a boundedness/escape threshold for the fourth body. In addition, we monitor total energy and total angular momentum as diagnostics of numerical integrity and physical consistency. A parameter scan over the fourth-body mass and speed produces a stability map that highlights rapid destabilization in most of the explored regions, with narrow islands of longer stability. Representative trajectory plots show that low-speed injections tend to produce close encounters, moderate speeds can yield bounded motion for longer times, and high speeds often result in escape (unbound trajectories). The results demonstrate how small perturbations can preserve the choreography over long integration windows, while stronger perturbations trigger chaotic scattering and a sharp reduction in stability time.
- 24 March 2026
- Published by Sciences Force in SciNexuses
- Vol. 3, 14-24
Open AccessInvestigating the Stability of a Perturbed Figure-8 Four-Body System Using Symplectic Integration
The figure-8 choreography of the equal-mass three-body problem is a rare example of a symmetric periodic solution in Newtonian gravity. In this study, we investigate the robustness of this orbit under a controlled perturbation: introducing a fourth body with variable mass and initial velocity while preserving the authorized figure-8 initial conditions for the original three bodies. We integrate the planar four-body equations of motion using a second-order symplectic leapfrog (velocity-Verlet) method to reduce long-term numerical drift in conserved quantities. Stability is quantified through a stability time defined by (i) a minimum pairwise-distance threshold to detect close encounters and (ii) a boundedness/escape threshold for the fourth body. In addition, we monitor total energy and total angular momentum as diagnostics of numerical integrity and physical consistency. A parameter scan over the fourth-body mass and speed produces a stability map that highlights rapid destabilization in most of the explored regions, with narrow islands of longer stability. Representative trajectory plots show that low-speed injections tend to produce close encounters, moderate speeds can yield bounded motion for longer times, and high speeds often result in escape (unbound trajectories). The results demonstrate how small perturbations can preserve the choreography over long integration windows, while stronger perturbations trigger chaotic scattering and a sharp reduction in stability time.
- Open Access
- 25 November 2025
- Published by Sciences Force in SciNexuses
- Vol. 2, 197-204
Stacking-Based Machine Learning Approach for Alzheimer's Disease Diagnosis
This study investigates the use of machine learning models for diagnosing Alzheimer's disease, based on the Alzheimer's Disease Dataset from Kaggle. The dataset includes a variety of features that are crucial for identifying Alzheimer's in patients. We applied different models such as Random Forest, Support Vector Machine (SVM), XGBoost, and a Stacking Model to predict the disease's presence. After evaluating the performance of each model, the Stacking Model emerged as the most accurate, achieving an impressive accuracy rate of 96%. This result demonstrates the potential of combining multiple models to improve diagnostic accuracy in Alzheimer's disease detection.
- 25 November 2025
- Published by Sciences Force in SciNexuses
- Vol. 2, 197-204
Open AccessStacking-Based Machine Learning Approach for Alzheimer's Disease Diagnosis
This study investigates the use of machine learning models for diagnosing Alzheimer's disease, based on the Alzheimer's Disease Dataset from Kaggle. The dataset includes a variety of features that are crucial for identifying Alzheimer's in patients. We applied different models such as Random Forest, Support Vector Machine (SVM), XGBoost, and a Stacking Model to predict the disease's presence. After evaluating the performance of each model, the Stacking Model emerged as the most accurate, achieving an impressive accuracy rate of 96%. This result demonstrates the potential of combining multiple models to improve diagnostic accuracy in Alzheimer's disease detection.
- Open Access
- 17 September 2025
- Published by Sciences Force in Information Sciences with Applications
- Vol. 7, 55-67
Heart Disease Prediction with Machine Learning Models: Superior Performance of Support Vector Machines
Heart disease results from long-term damage or inflammation affecting the heart and blood vessels, and it can impact individuals regardless of age, gender, or social background. Recent studies highlight approaches in identifying and predicting the risk of this condition. Such models estimate the probability of heart disease in percentage terms, enabling early detection and intervention. In this work, the dataset was processed using Python, and two primary algorithms Random Forest and Support Vector Machine (SVM) were applied for classification. While both methods produced promising outcomes, the SVM model achieved the highest performance, recording an accuracy of 95%. These results demonstrate the capability of machine learning techniques in enhancing the reliability of heart disease prediction.
- 17 September 2025
- Published by Sciences Force in Information Sciences with Applications
- Vol. 7, 55-67
Open AccessHeart Disease Prediction with Machine Learning Models: Superior Performance of Support Vector Machines
Heart disease results from long-term damage or inflammation affecting the heart and blood vessels, and it can impact individuals regardless of age, gender, or social background. Recent studies highlight approaches in identifying and predicting the risk of this condition. Such models estimate the probability of heart disease in percentage terms, enabling early detection and intervention. In this work, the dataset was processed using Python, and two primary algorithms Random Forest and Support Vector Machine (SVM) were applied for classification. While both methods produced promising outcomes, the SVM model achieved the highest performance, recording an accuracy of 95%. These results demonstrate the capability of machine learning techniques in enhancing the reliability of heart disease prediction.
- Open Access
- 29 May 2024
- Published by Sciences Force in SciNexuses
- Vol. 1, 44-51
Anticipating Diabetes using Fusion-Ensemble Machine Learning Techniques
Diagnosis of diabetes is still a complex task for most of the already existing machine learning methods. The objective of the study is to develop a decision support system for predicting the probability of diabetes disease. By using machine learning algorithms and considering fuzzy logic to handle uncertainty, a decision support system can be developed for predicting the probability of having diabetes in the given dataset. Diabetes patients will increase day by day; In current research, several algorithms have been used to predict diabetes. These are major issues for diabetes. Using these technologies, A model will be implemented to predict diabetes using different algorithms with proper comparison and find the best algorithm to predict diabetes. The prediction model is made using 11 classification algorithms from Ski learn, and their accuracies are compared. The expected result is that one of the best algorithms can be obtained for making a diabetes detection model. The fusion (ensemble) model is used for diabetes prediction, intended to improve the accuracy of classification. and use two algorithms to apply the fusion (ensemble) model, which picks the maximum accuracy of the list of classifiers with the rest of the classifiers. The source code is publicly accessible at https://github.com/diabetes-mellitus-implementation.
- 29 May 2024
- Published by Sciences Force in SciNexuses
- Vol. 1, 44-51
Open AccessAnticipating Diabetes using Fusion-Ensemble Machine Learning Techniques
Diagnosis of diabetes is still a complex task for most of the already existing machine learning methods. The objective of the study is to develop a decision support system for predicting the probability of diabetes disease. By using machine learning algorithms and considering fuzzy logic to handle uncertainty, a decision support system can be developed for predicting the probability of having diabetes in the given dataset. Diabetes patients will increase day by day; In current research, several algorithms have been used to predict diabetes. These are major issues for diabetes. Using these technologies, A model will be implemented to predict diabetes using different algorithms with proper comparison and find the best algorithm to predict diabetes. The prediction model is made using 11 classification algorithms from Ski learn, and their accuracies are compared. The expected result is that one of the best algorithms can be obtained for making a diabetes detection model. The fusion (ensemble) model is used for diabetes prediction, intended to improve the accuracy of classification. and use two algorithms to apply the fusion (ensemble) model, which picks the maximum accuracy of the list of classifiers with the rest of the classifiers. The source code is publicly accessible at https://github.com/diabetes-mellitus-implementation.
- 1 January 2024
- Published by American Scientific Publishing Group (ASPG) LLC in Journal of Sustainable Development and Green Technology
- Vol. 4 (1) , 16-22
Leveraging Business Intelligence for Enhanced Green Financial Practices in Advanced Corporations
American scientific publishing group
- 1 January 2024
- Published by American Scientific Publishing Group (ASPG) LLC in Journal of Sustainable Development and Green Technology
- Vol. 4 (1) , 16-22
Leveraging Business Intelligence for Enhanced Green Financial Practices in Advanced Corporations
American scientific publishing group
- Open Access
- 25 October 2023
- Published by Sciences Force - DIGITAL COMMONS JOURNALS in Sustainable Machine Intelligence Journal
- Vol. 5
A Comparative Analysis of Machine Learning Models for Prediction of Chronic Kidney Disease
Prediction of chronic kidney disease (CKD) has emerged as a useful technique for early detection of at-risk persons and the introduction of appropriate management strategies. Machine learning and data-driven methods have been used in predictive modeling to examine massive databases of patient demographics, medical histories, test findings, and genetic information. These cutting-edge methods allow for the profiling of high-risk patients and the tailoring of healthcare administration approaches. Patient outcomes, complication rates, and healthcare system efficiency may all benefit greatly from CKD screening and prediction. Responsible use of CKD prediction algorithms, however, requires resolving issues with data availability, integration, and ethics. The area of medicine has benefited greatly from the use of Machine Learning (ML) methods, which have played an increasingly central role in illness prediction. In this study, we use a strategy that makes use of ML methods to construct effective tools for predicting the development of CKD. Multiple ML models are trained, and their results are compared using a variety of criteria. We applied five ML methods such as logistic regression (LR), Decision tree (DT), random forest (RF), support vector machine (SVM), and k-nearest neighbor (KNN). The LR and KNN have the highest accuracy with 99%.
- 25 October 2023
- Published by Sciences Force - DIGITAL COMMONS JOURNALS in Sustainable Machine Intelligence Journal
- Vol. 5
Open AccessA Comparative Analysis of Machine Learning Models for Prediction of Chronic Kidney Disease
Prediction of chronic kidney disease (CKD) has emerged as a useful technique for early detection of at-risk persons and the introduction of appropriate management strategies. Machine learning and data-driven methods have been used in predictive modeling to examine massive databases of patient demographics, medical histories, test findings, and genetic information. These cutting-edge methods allow for the profiling of high-risk patients and the tailoring of healthcare administration approaches. Patient outcomes, complication rates, and healthcare system efficiency may all benefit greatly from CKD screening and prediction. Responsible use of CKD prediction algorithms, however, requires resolving issues with data availability, integration, and ethics. The area of medicine has benefited greatly from the use of Machine Learning (ML) methods, which have played an increasingly central role in illness prediction. In this study, we use a strategy that makes use of ML methods to construct effective tools for predicting the development of CKD. Multiple ML models are trained, and their results are compared using a variety of criteria. We applied five ML methods such as logistic regression (LR), Decision tree (DT), random forest (RF), support vector machine (SVM), and k-nearest neighbor (KNN). The LR and KNN have the highest accuracy with 99%.