Amira Rezk Abdo Rezk

@csifac.mans.edu.eg

information system department, faculty of computers and information , Mansoura university
faculty of computers and information , Mansoura university

Amira Rezk Abdo Rezk


                     Download Compact PDF  
https://researchid.co/amira_rezk

RESEARCH, TEACHING, or OTHER INTERESTS

Information Systems, Information Systems and Management, Computer Science Applications, Decision Sciences
28

Scopus Publications

652

Scholar Citations

13

Scholar h-index

16

Scholar i10-index

Scopus Publications

  • An intelligent system for abnormal human activity recognition in real-time
    Noura Abd El Nasser, Amira Rezk, Samaa Shohieb, Islam R. Abdelmaksoud
    Expert Systems with Applications, 2026
  • Geo-Blockchain Intelligence Risk Assessment (GBIRA) technologies for secure and sustainable internet of geospatial big data computing ecosystems: a survey
    Hana M. Saraya, Ahmed A. Saleh, Amira Rezk
    Geojournal, 2026
    In a world driven by geospatial big data, simulating past, present, and future scenarios is increasingly viable, giving rise to advanced geospatial intelligence sciences and technologies. These innovations enhance geospatial data management, which constitutes 80% of global data and is vital for addressing natural hazards like global warming and climate change, key areas of spatial big data research tied to environmental challenges. However, the growth of geospatial big data, associated with advancements in cloud computing, has increased cyberattack risks. Each technology for managing geospatial data has its complexities, benefits, and limitations. This paper examines Geo-Blockchain Intelligence Risk Assessment technologies, focusing on secure and sustainable geospatial big data computing for predicting environmental disasters in smart IoT ecosystems. It also explores new computing paradigms, providing robust capabilities to transform how environmental disasters and human responses interact through a comprehensive theoretical and scientific framework.
  • Improved chi-square feature selection for robust heart disease data classification
    Heba Nayl, , Elkhateeb S. Aly, Amira Rezk, M. E. Fares, , , and
    Aims Mathematics, 2026
    Early diagnosis of heart disease is vital for reducing mortality and improving patient outcomes; yet, accurate prediction remains a significant challenge owing to the complexity and high dimensionality of medical data. Data preprocessing is essential for overcoming these issues by cleaning, transforming, reducing, and balancing data to provide reliable inputs for feature selection and classification. This study introduces an improved chi-square ($ \chi^{2} $) feature selection framework combined with multiple classifiers to enhance predictive performance. Our method was applied to Cleveland heart disease and diabetes datasets, where numeric attributes were discretized into categorical values, enabling $ \chi^{2} $ to select the most informative features while eliminating redundancy. Several classifiers, including support vector machine (SVM), logistic regression (LR), K-nearest neighbors (KNN), and naive Bayes (NB), were trained using both the reduced subset and the complete feature set. Results show that the preprocessing include $ \chi^{2} $ feature selection, achieved the highest performance. On the Cleveland dataset, the model attained a mean accuracy of 93.72%, precision of 94.01%, recall of 93.72%, F1-score of 93.74%, and an area under the curve(AUC) of 97.87%, while on the diabetes dataset, it achieved mean values of 93.55% accuracy, 94.23% precision, 93.55% recall, 93.48% F1-score, and an AUC 93.53%. The main contribution of this work lies in integrating discretization with $ \chi^{2} $ based selection to produce a compact and discriminative feature subset. With a minimal number of selected features, the proposed approach delivers robust, accurate, and computationally efficient heart disease prediction, outperforming existing methods.
  • Geo blockchain intelligence risk assessment for extreme weather prediction in the era of internet of spatial big data computing
    Hana M. Saraya, Ahmed Abou-elfetouh Saleh, Amira Rezk
    Discover Internet of Things, 2025
    Global warming and climate change are widely researched due to their role in environmental disasters. Analyzing geospatial climate data has become critical for organizations, but the volume of geospatial data generated poses significant storage, processing, and analytical challenges for existing algorithms. Among extreme weather factors, temperature has profound impacts on human activities and industries. However, predicting extreme temperatures remains difficult due to the complex interplay of climate variables. This paper proposes a Geo-Blockchain Intelligence Risk Assessment (GBIRA) framework to predict extreme weather temperatures. GBIRA integrates Blockchain, AI, risk assessment, Spatial Big Data, cloud computing, and IoT to develop a Climate Intelligence prediction model. The framework aids in climate-related decision-making by assessing risks (e.g., extreme temperatures) and their impacts on critical assets. Additionally, it introduces GBIRA-as-a-Service, a novel computing paradigm that enhances environmental-human interaction through advanced theoretical and scientific methods. By efficiently processing and securing large-scale geospatial data, the framework improves extreme weather forecasting and risk assessment, ultimately supporting disaster response efforts. This research contributes to disaster risk management by providing a secure, scalable framework for real-time extreme weather prediction. The GBIRA framework offers practical applications for smart cities, agriculture, and emergency response systems, enabling more proactive climate adaptation strategies. The integration of blockchain with spatial big data computing establishes new standards for data integrity and interoperability in environmental monitoring, while the homomorphic encryption approach ensures privacy-preserving collaborative weather forecasting across organizational boundaries.
  • Enhancing customer retention in Online Retail through churn prediction: A hybrid RFM, K-means, and deep neural network approach
    Maha Zaghloul, Sherif Barakat, Amira Rezk
    Expert Systems with Applications, 2025
  • An effective SQL injection detection model using LSTM for imbalanced datasets
    Kholood Salah Fathi, Sherif Barakat, Amira Rezk
    Computers and Security, 2025
  • Automated lung cancer diagnosis from chest X-ray images using convolutional neural networks
    Aya Aboelghiet, Samaa M. Shohieb, Amira Rezk, Ahmed Abou Elfetouh, Ahmed Sharaf, Islam Abdelmaksoud
    Peerj Computer Science, 2025
    Background/Objectives Lung cancer is the leading cause of cancer-related deaths worldwide. While computed tomography (CT) scans provide more comprehensive medical information than chest X-rays (CXR), the high cost and limited availability of CT technology in rural areas pose significant challenges. CXR images, however, could serve as a potential preliminary diagnostic tool in diagnosing lung cancer, especially when combined with a computer-aided diagnosis (CAD) system. This study aims to enhance the accuracy and accessibility of lung cancer detection using a custom-designed convolutional neural network (CNN) trained on CXR images. Methods A custom-designed CNN was trained on an openly accessible CXR dataset from the Japanese Society for Radiological Technology (JSRT). Prior to training, the dataset underwent preprocessing, where each image was divided into overlapping patches. A t-test was applied to these patches to distinguish relevant from irrelevant ones. The relevant patches were retained for training the CNN model, while the irrelevant patches were excluded to enhance the model’s performance. Results The proposed model yielded a mean accuracy of 83.2 ± 2.91%, demonstrating its potential as a cost-effective and accessible preliminary diagnostic tool for lung cancer. Conclusions This approach could significantly improve the accuracy and accessibility of lung cancer detection, making it a viable option in resource-limited settings.
  • Predicting E-commerce customer satisfaction: Traditional machine learning vs. deep learning approaches
    Maha Zaghloul, Sherif Barakat, Amira Rezk
    Journal of Retailing and Consumer Services, 2024
  • A generalized ensemble approach based on transfer learning for Braille character recognition
    Nagwa Elaraby, Sherif Barakat, Amira Rezk
    Information Processing and Management, 2024
  • Enhanced Optimized Classification Model of Chronic Kidney Disease
    Shahinda Elkholy, Amira Rezk, Ahmed Abo El Fetoh Saleh
    International Journal of Advanced Computer Science and Applications, 2023
    —Chronic kidney disease (CKD) is one of the leading causes of death across the globe, affecting about 10% of the world's adult population. Kidney disease affects the proper function of the kidneys. As the number of people with chronic kidney disease (CKD) rises, it is becoming increasingly important to have accurate methods for detecting CKD at an early stage. Developing a mechanism for detecting chronic kidney disease is the study's main contribution to knowledge. In this study, preventive interventions for CKD can be explored using machine learning techniques (ML). The Optimized deep belief network (DBN) based on Grasshopper's Optimization Algorithm (GOA) classifier with prior Density-based Feature Selection (DFS) algorithm for chronic kidney disease is described in this study, which is called "DFS-ODBN." Prior to the DBN classifier, whose parameters are optimized using GOA, the proposed method eliminates redundant or irrelevant dimensions using DFS. The proposed DFS-ODBN framework consists of three phases, preprocessing, feature selection, and classification phases. Using CKD datasets, the suggested approach is also tested, and the performance is evaluated using several assessment metrics. Optimized-DBN achieves its maximum performance in terms of sensitivity, accuracy, and specificity, the proposed DFS-ODBN demonstrated accuracy of 99.75 percent using fewer features comparing with other techniques.
  • Effective E-commerce Based on Predicting the Level of Consumer Satisfaction
    Maha Fouad, Sherif Barakat, Amira Rezk
    Lecture Notes in Networks and Systems, 2023
  • A Novel Siamese Network for Few/Zero-Shot Handwritten Character Recognition Tasks
    Nagwa Elaraby, Sherif Barakat, Amira Rezk
    Computers Materials and Continua, 2023
  • Towards a deep learning-based outlier detection approach in the context of streaming data
    Asmaa F. Hassan, Sherif Barakat, Amira Rezk
    Journal of Big Data, 2022
  • A conditional GAN-based approach for enhancing transfer learning performance in few-shot HCR tasks
    Nagwa Elaraby, Sherif Barakat, Amira Rezk
    Scientific Reports, 2022
  • Different Scales of Medical Data Classification Based on Machine Learning Techniques: A Comparative Study
    Heba Aly Elzeheiry, Sherief Barakat, Amira Rezk
    Applied Sciences Switzerland, 2022
  • An Effective Ensemble-based Framework for Outlier Detection in Evolving Data Streams
    Asmaa F. Hassan, Sherif Barakat, Amira Rezk
    International Journal of Advanced Computer Science and Applications, 2022
  • An Efficient Ensemble Model for Various Scale Medical Data
    Heba A. Elzeheiry, Sherief Barakat, Amira Rezk
    Computers Materials and Continua, 2022
  • Towards an Accurate Breast Cancer Classification Model based on Ensemble Learning
    Aya Hesham, Nora El-Rashidy, Amira Rezk, Noha A. Hikal
    International Journal of Advanced Computer Science and Applications, 2022
  • Toward a universal electronic health record system
    Aya Gamal, Sherif Barakat, Amira Rezk
    Journal of Biomedical Informatics, 2021
  • Real-time big data clustering using spark: Uber case study
    Journal of Theoretical and Applied Information Technology, 2021
  • Standardized electronic health record data modeling and persistence: A comparative review
    Aya Gamal, Sherif Barakat, Amira Rezk
    Journal of Biomedical Informatics, 2021
  • Early Prediction of Chronic Kidney Disease Using Deep Belief Network
    Shahinda Mohamed Mostafa Elkholy, Amira Rezk, Ahmed Abo El Fetoh Saleh
    IEEE Access, 2021
  • Integrated Document-based Electronic Health Records Persistence Framework
    Aya Gamal, Sherif Barakat, Amira Rezk
    International Journal of Advanced Computer Science and Applications, 2021
  • A transfer learning-enabled optimized extreme deep learning paradigm for diagnosis of COVID-19
    Ahmed Reda, Sherif Barakat, Amira Rezk
    Computers Materials and Continua, 2021
  • An Improved K-anonymization Approach for Preserving Graph Structural Properties
    A. Mohammed Hanafy, Sherif Barakat, Amira Rezk
    International Journal of Advanced Computer Science and Applications, 2021
  • A Comprehensive Fuzzy Ontology-Based Decision Support System for Alzheimer's Disease Diagnosis
    Nora Shoaip, Amira Rezk, Shaker El-Sappagh, Louai Alarabi, Sherif Barakat, Mohammed M. Elmogy
    IEEE Access, 2021
  • Alzheimer's Disease Diagnosis Based on a Semantic Rule-Based Modeling and Reasoning Approach
    Nora Shoaip, Amira Rezk, Shaker EL-Sappagh, Tamer Abuhmed, Sherif Barakat, Mohammed Elmogy
    Computers Materials and Continua, 2021
  • Adaptive classification in data stream mining
    Journal of Theoretical and Applied Information Technology, 2020

RECENT SCHOLAR PUBLICATIONS

  • Geo-Blockchain Intelligence Risk Assessment (GBIRA) technologies for secure and sustainable internet of geospatial big data computing ecosystems: a survey
    HM Saraya, AA Saleh, A Rezk
    GeoJournal 91 (2), 43 , 2026
    2026
  • Improved chi-square feature selection for robust heart disease data classification
    H Nayl, ES Aly, A Rezk, ME Fares
    AIMS Mathematics 11 (1), 2682-2701 , 2026
    2026
  • A Novel Hybrid CNN-LSTM Framework for Robust DDoS Attack Detection and Classification.
    A OK Al-Hasani, I R Abdelmaksoud, A Rezk
    Journal of Cybersecurity & Information Management 17 (1) , 2026
    2026
    Citations: 1
  • Geo blockchain intelligence risk assessment for extreme weather prediction in the era of internet of spatial big data computing
    HM Saraya, AA Saleh, A Rezk
    Discover Internet of Things 5 (1), 145 , 2025
    2025
    Citations: 3
  • Enhancing customer retention in Online Retail through churn prediction: A hybrid RFM, K-means, and deep neural network approach
    M Zaghloul, S Barakat, A Rezk
    Expert Systems With Applications 290, 128465 , 2025
    2025
    Citations: 21
  • Automated lung cancer diagnosis from chest X-ray images using convolutional neural networks
    A Aboelghiet, SM Shohieb, A Rezk, A Abou Elfetouh, A Sharaf, ...
    PeerJ Computer Science 11, e3145 , 2025
    2025
  • Enhancing fraud detection in imbalanced datasets: A comparative study of machine learning and deep learning algorithms with SMOTE preprocessing
    WS Salem, I El-Hasnony, A Abu Elfetouh, A Rezk
    Mansoura Journal for Computer and Information Sciences 20 (1), 1-21 , 2025
    2025
    Citations: 6
  • An effective SQL injection detection model using LSTM for imbalanced datasets
    KS Fathi, S Barakat, A Rezk
    Computers & Security 153, 104391 , 2025
    2025
    Citations: 15
  • Predicting E-commerce customer satisfaction: Traditional machine learning vs. deep learning approaches
    M Zaghloul, S Barakat, A Rezk
    Journal of Retailing and Consumer Services 79, 103865 , 2024
    2024
    Citations: 93
  • A generalized ensemble approach based on transfer learning for Braille character recognition
    N Elaraby, S Barakat, A Rezk
    Information Processing & Management 61 (1), 103545 , 2024
    2024
    Citations: 29
  • on Predicting the Level of Consumer
    M Fouad, S Barakat, A Rezk
    Green Sustainability: Towards Innovative Digital Transformation: Proceedings … , 2023
    2023
  • A novel Siamese network for few/zero-shot handwritten character recognition tasks
    N Elaraby, S Barakat, A Rezk
    Computers, Materials & Continua , 2023
    2023
    Citations: 12
  • Effective e-commerce based on predicting the level of consumer satisfaction
    M Fouad, S Barakat, A Rezk
    World Conference on Internet of Things: Applications & Future, 261-278 , 2023
    2023
    Citations: 5
  • Enhanced optimized classification model of chronic kidney disease
    S Elkholy, A Rezk, AAEF Saleh
    International Journal of Advanced Computer Science and Applications 14 (2) , 2023
    2023
    Citations: 5
  • Towards a deep learning-based outlier detection approach in the context of streaming data
    AF Hassan, S Barakat, A Rezk
    Journal of Big Data 9 (1), 120 , 2022
    2022
    Citations: 23
  • An Efficient Ensemble Model for Various Scale Medical Data.
    HA Elzeheiry, S Barakat, A Rezk
    Computers, Materials & Continua 73 (1) , 2022
    2022
    Citations: 2
  • A conditional GAN-based approach for enhancing transfer learning performance in few-shot HCR tasks
    N Elaraby, S Barakat, A Rezk
    Scientific reports 12 (1), 16271 , 2022
    2022
    Citations: 35
  • Different scales of medical data classification based on machine learning techniques: a comparative study
    HA Elzeheiry, S Barakat, A Rezk
    Applied Sciences 12 (2), 919 , 2022
    2022
    Citations: 19
  • Towards an accurate breast cancer classification model based on ensemble learning
    A Hesham, N El-Rashidy, A Rezk, NA Hikal
    International Journal of Advanced Computer Science and Applications 13 (12) , 2022
    2022
    Citations: 1
  • An effective ensemble-based framework for outlier detection in evolving data streams
    AF Hassan, S Barakat, A Rezk
    International Journal of Advanced Computer Science and Applications 13 (11 … , 2022
    2022
    Citations: 6

MOST CITED SCHOLAR PUBLICATIONS

  • Early prediction of chronic kidney disease using deep belief network
    SMM Elkholy, A Rezk, AAEF Saleh
    IEEE Access 9, 135542-135549 , 2021
    2021
    Citations: 109
  • Standardized electronic health record data modeling and persistence: A comparative review
    A Gamal, S Barakat, A Rezk
    Journal of biomedical informatics 114, 103670 , 2021
    2021
    Citations: 108
  • Predicting E-commerce customer satisfaction: Traditional machine learning vs. deep learning approaches
    M Zaghloul, S Barakat, A Rezk
    Journal of Retailing and Consumer Services 79, 103865 , 2024
    2024
    Citations: 93
  • An Efficient Classification Model for Unstructured Text Document
    M Mowafy, A Rezk, HM El-bakry
    Am J Compt Sci Inform Technol 6 (1), 16 , 2018
    2018
    Citations: 39
  • A conditional GAN-based approach for enhancing transfer learning performance in few-shot HCR tasks
    N Elaraby, S Barakat, A Rezk
    Scientific reports 12 (1), 16271 , 2022
    2022
    Citations: 35
  • A comprehensive fuzzy ontology-based decision support system for Alzheimer’s disease diagnosis
    N Shoaip, A Rezk, S El-Sappagh, L Alarabi, S Barakat, MM Elmogy
    IEEE Access 9, 31350-31372 , 2020
    2020
    Citations: 30
  • A generalized ensemble approach based on transfer learning for Braille character recognition
    N Elaraby, S Barakat, A Rezk
    Information Processing & Management 61 (1), 103545 , 2024
    2024
    Citations: 29
  • Towards a deep learning-based outlier detection approach in the context of streaming data
    AF Hassan, S Barakat, A Rezk
    Journal of Big Data 9 (1), 120 , 2022
    2022
    Citations: 23
  • The impact of cyber crime on E-Commerce
    A Rezk, S Barakat, H Saleh
    International Journal of Intelligent Computing and Information Sciences 17 … , 2017
    2017
    Citations: 23
  • Enhancing customer retention in Online Retail through churn prediction: A hybrid RFM, K-means, and deep neural network approach
    M Zaghloul, S Barakat, A Rezk
    Expert Systems With Applications 290, 128465 , 2025
    2025
    Citations: 21
  • Different scales of medical data classification based on machine learning techniques: a comparative study
    HA Elzeheiry, S Barakat, A Rezk
    Applied Sciences 12 (2), 919 , 2022
    2022
    Citations: 19
  • Alzheimer’s disease diagnosis based on a semantic rule-based modeling and reasoning approach
    N Shoaip, A Rezk, S El-Sappagh, T Abuhmed, S Barakat, M Elmogy
    Computers, Materials, & Continua 69 (3), 3531 , 2021
    2021
    Citations: 18
  • An effective SQL injection detection model using LSTM for imbalanced datasets
    KS Fathi, S Barakat, A Rezk
    Computers & Security 153, 104391 , 2025
    2025
    Citations: 15
  • A novel Siamese network for few/zero-shot handwritten character recognition tasks
    N Elaraby, S Barakat, A Rezk
    Computers, Materials & Continua , 2023
    2023
    Citations: 12
  • Letter to Editor (Response from author): Toward a universal electronic health record system
    A Gamal, S Barakat, A Rezk
    Journal of Biomedical Informatics 117, 103770 , 2021
    2021
    Citations: 10
  • Minimize the false positive rate in a database intrusion detection system
    A Rezk, H Ali, M El-Mikkawy, S Barakat
    International Journal of Computer Science & Information Technology 3 (5), 29 , 2011
    2011
    Citations: 10
  • A transfer learning-enabled optimized extreme deep learning paradigm for diagnosis of covid-19
    R Ahmed, S Barakat, A Rezk
    Computers, Materials, & Continua 70 (1), 1381 , 2022
    2022
    Citations: 7
  • Enhancing fraud detection in imbalanced datasets: A comparative study of machine learning and deep learning algorithms with SMOTE preprocessing
    WS Salem, I El-Hasnony, A Abu Elfetouh, A Rezk
    Mansoura Journal for Computer and Information Sciences 20 (1), 1-21 , 2025
    2025
    Citations: 6
  • An effective ensemble-based framework for outlier detection in evolving data streams
    AF Hassan, S Barakat, A Rezk
    International Journal of Advanced Computer Science and Applications 13 (11 … , 2022
    2022
    Citations: 6
  • Effective e-commerce based on predicting the level of consumer satisfaction
    M Fouad, S Barakat, A Rezk
    World Conference on Internet of Things: Applications & Future, 261-278 , 2023
    2023
    Citations: 5