Huda Amin Maghawry
Huda Amin Maghawry has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Nagwa Badr
Information Systems Department, Faculty of Computer and Information Sciences, Ain Shams University, Cairo 11566, Egypt
3 shared publications - Nagwa Badr
Department of Information Systems, Faculty of Computer and Information Sciences, Ain Shams University, Cairo, 11566, Egypt
3 shared publications - Tarek F. Gharib
Ain Shams University
3 shared publications - Amira Ali
Faculty of Computer and Information Science Ain Shams University Cairo Egypt
2 shared publications - Amira Samir
Department of Information Systems, Faculty of Computer and Information Sciences, Ain Shams University, Cairo, Egypt
2 shared publications - Mohamed Farouk Yacoub
Information Systems Department, Faculty of Computer and Information Sciences, Ain Shams University, Cairo 11566, Egypt
2 shared publications
Latest Publications
- Open Access
- 31 March 2024
- Published by Egyptian Knowledge Bank in International Journal of Intelligent Computing and Information Sciences
- Vol. 24 (1) , 89-104
Integration of Deep Learning Models for Enhanced Classification of Viral DNA Sequences Across Specific Viruses and Viral Families
The field of genomic bioinformatics is continually challenged by the need for precise classification of viral DNA sequences. The challenge of accurately classifying viral sequences is crucial for the development of diagnostic and therapeutic strategies for any viral outbreaks. This study presents a comprehensive approach integrating two distinct deep learning models, namely the Genetic Algorithm (GA) optimized Convolutional Neural Networks (CNN) hybrid model and the CNN-Extreme Learning Machines (ELM) model aiming to enhance the classification of viral DNA sequences across specific viruses and viral families. A comprehensive data preprocessing strategy is employed, wherein both datasets undergo k-mer, label, and one-hot vector encoding. This allows for a uniform and comparative analysis across different models and datasets. When the optimized GA-CNN is applied to the more generic viral family dataset, it demonstrates a good adaptability with an accuracy of 95.88% achieving a higher result than the CNN-ELM. In contrast, the CNN-ELM, when tested on the specific virus dataset, maintains robust feature extraction capabilities, faster training time but lower than the optimized GA-CNN model achieving an accuracy of 92.7%.A comparative analysis of training times is also employed in this study. The CNN-ELM model shows a notable efficiency, with a 34% faster training time compared to the GA-CNN. Moreover, when both models are applied to the new generic dataset, a comparative study with other deep learning models is conducted. Remarkably, the GA-CNN outperforms other models, achieving the highest classification accuracy of 95.88%.
- 31 March 2024
- Published by Egyptian Knowledge Bank in International Journal of Intelligent Computing and Information Sciences
- Vol. 24 (1) , 89-104
Open AccessIntegration of Deep Learning Models for Enhanced Classification of Viral DNA Sequences Across Specific Viruses and Viral Families
The field of genomic bioinformatics is continually challenged by the need for precise classification of viral DNA sequences. The challenge of accurately classifying viral sequences is crucial for the development of diagnostic and therapeutic strategies for any viral outbreaks. This study presents a comprehensive approach integrating two distinct deep learning models, namely the Genetic Algorithm (GA) optimized Convolutional Neural Networks (CNN) hybrid model and the CNN-Extreme Learning Machines (ELM) model aiming to enhance the classification of viral DNA sequences across specific viruses and viral families. A comprehensive data preprocessing strategy is employed, wherein both datasets undergo k-mer, label, and one-hot vector encoding. This allows for a uniform and comparative analysis across different models and datasets. When the optimized GA-CNN is applied to the more generic viral family dataset, it demonstrates a good adaptability with an accuracy of 95.88% achieving a higher result than the CNN-ELM. In contrast, the CNN-ELM, when tested on the specific virus dataset, maintains robust feature extraction capabilities, faster training time but lower than the optimized GA-CNN model achieving an accuracy of 92.7%.A comparative analysis of training times is also employed in this study. The CNN-ELM model shows a notable efficiency, with a 34% faster training time compared to the GA-CNN. Moreover, when both models are applied to the new generic dataset, a comparative study with other deep learning models is conducted. Remarkably, the GA-CNN outperforms other models, achieving the highest classification accuracy of 95.88%.
- Open Access
- 1 December 2023
- Published by Egyptian Knowledge Bank in International Journal of Intelligent Computing and Information Sciences
- Vol. 23 (4) , 33-49
ENHANCED REGRESSION TESTING EXECUTION PROCESS USING TEST SUITE REDUCTION TECHNIQUES AND PARALLEL EXECUTION
Regression testing is a vital category of software testing. Regression testing is done to make sure that changed code does not have any unexpected negative effects on the software. Regression testing, despite its significance in ensuring software quality, can be a costly phase in the software testing process. Typically, the more tests there are, the longer it takes for them to run. As a result, the price of regression testing rises with the quantity of tests. So, the objective is to reduce execution time of the regression testing by removing test cases that are redundant or have lower importance in terms of their capacity to uncover faults. The primary aim of test case reduction is to decrease the number of test cases, which, in turn, lowers the time and expenses associated with their execution. This paper presents an approach to minimize the execution time of regression testing while preserving code coverage, achieved through the utilization of test suite reduction techniques and parallel automation execution. The employed test suite reduction approach involves utilizing a clustering technique and a genetic algorithm. The resulting reduced test suite is then executed in parallel to achieve the shortest possible execution time. The results demonstrate that the proposed approach can cut down execution time by 75%.
- 1 December 2023
- Published by Egyptian Knowledge Bank in International Journal of Intelligent Computing and Information Sciences
- Vol. 23 (4) , 33-49
Open AccessENHANCED REGRESSION TESTING EXECUTION PROCESS USING TEST SUITE REDUCTION TECHNIQUES AND PARALLEL EXECUTION
Regression testing is a vital category of software testing. Regression testing is done to make sure that changed code does not have any unexpected negative effects on the software. Regression testing, despite its significance in ensuring software quality, can be a costly phase in the software testing process. Typically, the more tests there are, the longer it takes for them to run. As a result, the price of regression testing rises with the quantity of tests. So, the objective is to reduce execution time of the regression testing by removing test cases that are redundant or have lower importance in terms of their capacity to uncover faults. The primary aim of test case reduction is to decrease the number of test cases, which, in turn, lowers the time and expenses associated with their execution. This paper presents an approach to minimize the execution time of regression testing while preserving code coverage, achieved through the utilization of test suite reduction techniques and parallel automation execution. The employed test suite reduction approach involves utilizing a clustering technique and a genetic algorithm. The resulting reduced test suite is then executed in parallel to achieve the shortest possible execution time. The results demonstrate that the proposed approach can cut down execution time by 75%.
- Open Access
- 1 June 2023
- Published by Egyptian Knowledge Bank in International Journal of Intelligent Computing and Information Sciences
- Vol. 23 (2) , 1-12
Survey of Liver Fibrosis Prediction Using Machine Learning Techniques
The prediction of liver fibrosis stages in Hepatitis C virus (HCV) and Hepatitis B virus (HBV) is an important issue. The gold criterion for liver fibrosis stages evaluation is the liver biopsy but with a lot of drawbacks. So, it became necessary to use alternative methods to assess the degree of liver fibrosis. Many machine learning techniques were used as non-invasive alternative methods for doing the liver fibrosis prediction task to avoid the disadvantages of the liver biopsy. This study surveys many machine learning techniques that were applied for differentiation between the stages of hepatic fibrosis and liver fibrosis prediction on different medical HBV and HCV datasets using different blood tests and clinical parameters with applying several feature selection techniques. Also, the results and performance of classifier models are reviewed with comparison to non-invasive methods, which used for liver fibrosis prediction, such as APRI score and FIB-4 index score.
- 1 June 2023
- Published by Egyptian Knowledge Bank in International Journal of Intelligent Computing and Information Sciences
- Vol. 23 (2) , 1-12
Open AccessSurvey of Liver Fibrosis Prediction Using Machine Learning Techniques
The prediction of liver fibrosis stages in Hepatitis C virus (HCV) and Hepatitis B virus (HBV) is an important issue. The gold criterion for liver fibrosis stages evaluation is the liver biopsy but with a lot of drawbacks. So, it became necessary to use alternative methods to assess the degree of liver fibrosis. Many machine learning techniques were used as non-invasive alternative methods for doing the liver fibrosis prediction task to avoid the disadvantages of the liver biopsy. This study surveys many machine learning techniques that were applied for differentiation between the stages of hepatic fibrosis and liver fibrosis prediction on different medical HBV and HCV datasets using different blood tests and clinical parameters with applying several feature selection techniques. Also, the results and performance of classifier models are reviewed with comparison to non-invasive methods, which used for liver fibrosis prediction, such as APRI score and FIB-4 index score.
- Open Access
- 28 February 2023
- Published by Pensoft Publishers in JUCS - Journal of Universal Computer Science
- Vol. 29 (2) , 152-178
An Enhanced Testing Approach for Mobile Applications
Nowadays, there is an enormous number of mobile applications that are continuously being launched to the market. As a result of this rapid process, there is a need to increase the speed of testing process using enhanced approaches. This research aims to increase the effectiveness of the graphical user interface testing process of mobile applications. This is achieved by proposing an enhanced combinatorial-based metaheuristic approach. The proposed approach aims to maximize statement and branch coverage by applying Cuckoo search, for event selection. The approach was compared to monkey, frequency, random and greedy approaches. Experiments were conducted on different mobile applications. During the same testing time duration, the proposed approach achieved higher coverage than the other approaches. The proposed approach proved its effectiveness in mobile application testing compared to the other approaches.
- 28 February 2023
- Published by Pensoft Publishers in JUCS - Journal of Universal Computer Science
- Vol. 29 (2) , 152-178
Open AccessAn Enhanced Testing Approach for Mobile Applications
Nowadays, there is an enormous number of mobile applications that are continuously being launched to the market. As a result of this rapid process, there is a need to increase the speed of testing process using enhanced approaches. This research aims to increase the effectiveness of the graphical user interface testing process of mobile applications. This is achieved by proposing an enhanced combinatorial-based metaheuristic approach. The proposed approach aims to maximize statement and branch coverage by applying Cuckoo search, for event selection. The approach was compared to monkey, frequency, random and greedy approaches. Experiments were conducted on different mobile applications. During the same testing time duration, the proposed approach achieved higher coverage than the other approaches. The proposed approach proved its effectiveness in mobile application testing compared to the other approaches.
- Open Access
- 7 December 2022
- Published by Egyptian Knowledge Bank in International Journal of Intelligent Computing and Information Sciences
- p. 1-16
Automation of Performance Testing: A Review
Quality assurance of software applications becomes crucial for achieving a competitive advantage in the market. Automating the testing process reduces the required cost and human effort. However, automating the entire testing process still challenging to both academia and industry. It is essential to verify the robustness of the application under test (AUT) by conducting the performance testing. Performance testing is a non-functional form of software testing which examines the performance features of the AUT when exposed to various workloads. The performance behavior can be measured by throughput, response time, and resource utilization of the AUT under a certain workload. Besides, performance testing finds the performance breaking points and bottlenecks during the operation of the AUT. Due to the necessity of conducting performance testing before releasing applications to the market, this paper surveys the previous related work to the performance testing since 2009. Recent studied related to performance testing for testing both mobile and web-based applications are discussed. The strengths and weaknesses of these studies are discussed. Besides, a comparison between the previous studies related to the performance testing is held from different perspectives.
- 7 December 2022
- Published by Egyptian Knowledge Bank in International Journal of Intelligent Computing and Information Sciences
- p. 1-16
Open AccessAutomation of Performance Testing: A Review
Quality assurance of software applications becomes crucial for achieving a competitive advantage in the market. Automating the testing process reduces the required cost and human effort. However, automating the entire testing process still challenging to both academia and industry. It is essential to verify the robustness of the application under test (AUT) by conducting the performance testing. Performance testing is a non-functional form of software testing which examines the performance features of the AUT when exposed to various workloads. The performance behavior can be measured by throughput, response time, and resource utilization of the AUT under a certain workload. Besides, performance testing finds the performance breaking points and bottlenecks during the operation of the AUT. Due to the necessity of conducting performance testing before releasing applications to the market, this paper surveys the previous related work to the performance testing since 2009. Recent studied related to performance testing for testing both mobile and web-based applications are discussed. The strengths and weaknesses of these studies are discussed. Besides, a comparison between the previous studies related to the performance testing is held from different perspectives.
- 18 November 2022
- Published by Springer Nature
- p. 107-122
An Efficient 2-Stages Classification Model for Students Performance Prediction
- 18 November 2022
- Published by Springer Nature
- p. 107-122
An Efficient 2-Stages Classification Model for Students Performance Prediction
- 1 August 2022
- Published by Egyptian Knowledge Bank in International Journal of Intelligent Computing and Information Sciences
- Vol. 22 (3) , 124-137
PREDICTING STUDENTS’ PERFORMANCE USING AN ENHANCED AGGREGATION STRATEGY FOR SUPERVISED MULTICLASS CLASSIFICATION
Predicting students performance efficiently became one of the most interesting research topics. Efficiently mining the educational data is the cornerstone and the first step to make the appropriate intervention to help at-risk students achieve better performance and enhance the educational outcomes. The objective of this paper is to efficiently predict students’ performance by predicting their academic performance level. This is achieved by proposing an enhanced aggregation strategy on a supervised multiclass classification problem to improve the prediction accuracy of students’ performance. Two binary classification techniques: Support Vector Machine (SVM) and Perceptron algorithms, have been experimented to use their output as an input to the proposed aggregation strategy to be compared with a previously used aggregation strategy. The proposed strategy improved the prediction performance and achieved an accuracy, recall, and precision of 75.0%, 76.0%, and 75.48% using Perceptron, respectively. Moreover, The proposed strategy outperformed and achieved an accuracy, recall, and precision of 73.96%, 73.93%, and 75.33% using SVM, respectively.
- 1 August 2022
- Published by Egyptian Knowledge Bank in International Journal of Intelligent Computing and Information Sciences
- Vol. 22 (3) , 124-137
PREDICTING STUDENTS’ PERFORMANCE USING AN ENHANCED AGGREGATION STRATEGY FOR SUPERVISED MULTICLASS CLASSIFICATION
Predicting students performance efficiently became one of the most interesting research topics. Efficiently mining the educational data is the cornerstone and the first step to make the appropriate intervention to help at-risk students achieve better performance and enhance the educational outcomes. The objective of this paper is to efficiently predict students’ performance by predicting their academic performance level. This is achieved by proposing an enhanced aggregation strategy on a supervised multiclass classification problem to improve the prediction accuracy of students’ performance. Two binary classification techniques: Support Vector Machine (SVM) and Perceptron algorithms, have been experimented to use their output as an input to the proposed aggregation strategy to be compared with a previously used aggregation strategy. The proposed strategy improved the prediction performance and achieved an accuracy, recall, and precision of 75.0%, 76.0%, and 75.48% using Perceptron, respectively. Moreover, The proposed strategy outperformed and achieved an accuracy, recall, and precision of 73.96%, 73.93%, and 75.33% using SVM, respectively.
- 24 July 2022
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 34 (12)
Performance testing as a service using cloud computing environment: A survey
Cloud testing is gaining much attention in both academia and industry as an emerging concept in the field of software testing. Cloud testing implies leveraging the resources of the cloud computing environment to overcome deficiencies of the traditional testing approaches. As a result, testing‐as‐a‐service (TaaS) is introduced as a service model that conducts all testing activities in a fully automated manner using cloud‐based resources. Performance testing is a type of software testing that validates the performance characteristics of the application under test (AUT) when subjected to different workloads during its operation. Performance characteristics include throughput, response time, and resource utilization of the AUT under a certain workload. This paper focuses on reviewing the literature related to the provision of performance testing as a service (P‐TaaS). In this study, we survey the previous work related to cloud‐based performance testing. We show the strengths and weaknesses of the current research. Besides, we compare the P‐TaaS with the traditional performance testing methodologies. A detailed discussion of the benefits and challenges of P‐TaaS is introduced along with identifying the research gaps and the future directions that can be adopted.
- 24 July 2022
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 34 (12)
Performance testing as a service using cloud computing environment: A survey
Cloud testing is gaining much attention in both academia and industry as an emerging concept in the field of software testing. Cloud testing implies leveraging the resources of the cloud computing environment to overcome deficiencies of the traditional testing approaches. As a result, testing‐as‐a‐service (TaaS) is introduced as a service model that conducts all testing activities in a fully automated manner using cloud‐based resources. Performance testing is a type of software testing that validates the performance characteristics of the application under test (AUT) when subjected to different workloads during its operation. Performance characteristics include throughput, response time, and resource utilization of the AUT under a certain workload. This paper focuses on reviewing the literature related to the provision of performance testing as a service (P‐TaaS). In this study, we survey the previous work related to cloud‐based performance testing. We show the strengths and weaknesses of the current research. Besides, we compare the P‐TaaS with the traditional performance testing methodologies. A detailed discussion of the benefits and challenges of P‐TaaS is introduced along with identifying the research gaps and the future directions that can be adopted.
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 402-407
Enhanced Approach for Maximizing Coverage in Automated Mobile Application Testing
Nowadays, Smartphones are an important part of our lives. It is critical to ensure the quality of their applications. By the great increase in the number of mobile applications, it is important to speed up the testing process. This could be performed using automated approaches. In this paper, different enhancements have been proposed based on combinatorial testing approach by applying improved tie-breaking strategies in order to maximize the statement coverage. We have performed experiments within 15, 30 and 60 minutes to generate test cases. We have proved that the selection of candidate events based on their weight and using Last In First Out tie-breaking strategy in choosing the event to be executed maximizes the statement coverage of test cases.
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 402-407
Enhanced Approach for Maximizing Coverage in Automated Mobile Application Testing
Nowadays, Smartphones are an important part of our lives. It is critical to ensure the quality of their applications. By the great increase in the number of mobile applications, it is important to speed up the testing process. This could be performed using automated approaches. In this paper, different enhancements have been proposed based on combinatorial testing approach by applying improved tie-breaking strategies in order to maximize the statement coverage. We have performed experiments within 15, 30 and 60 minutes to generate test cases. We have proved that the selection of candidate events based on their weight and using Last In First Out tie-breaking strategy in choosing the event to be executed maximizes the statement coverage of test cases.
- 19 June 2018
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 30 (10)
Automated parallel GUI testing as a service for mobile applications
Recently, testing mobile applications is gaining much attention due to the widespread of smartphones and the tremendous number of mobile applications development. It is essential to test mobile applications before being released for the public use. Graphical user interface (GUI) testing is a type of mobile applications testing conducted to ensure the proper functionality of the GUI components. Typically, GUI testing requires a lot of effort and time whether manual or automatic. Cloud computing is an emerging technology that can be used in the software engineering field to overcome the defects of the traditional testing approaches by using cloud computing resources. As a result, testing‐as‐a‐service is introduced as a service model that conducts all testing activities in a fully automated manner. In this paper, a system for mobile applications GUI testing based on testing‐as‐a‐service architecture is proposed. The proposed system performs all testing activities including automatic test case generation and simultaneous test execution on multiple virtual nodes for testing Android‐based applications. The proposed system reduces testing time and meets fast time‐to market constraint of mobile applications. Moreover, the proposed system architecture addresses many issues such as maximizing resource utilization, continuous monitoring to ensure system reliability, and applying fault‐tolerance approach to handle occurrence of any failure.
- 19 June 2018
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 30 (10)
Automated parallel GUI testing as a service for mobile applications
Recently, testing mobile applications is gaining much attention due to the widespread of smartphones and the tremendous number of mobile applications development. It is essential to test mobile applications before being released for the public use. Graphical user interface (GUI) testing is a type of mobile applications testing conducted to ensure the proper functionality of the GUI components. Typically, GUI testing requires a lot of effort and time whether manual or automatic. Cloud computing is an emerging technology that can be used in the software engineering field to overcome the defects of the traditional testing approaches by using cloud computing resources. As a result, testing‐as‐a‐service is introduced as a service model that conducts all testing activities in a fully automated manner. In this paper, a system for mobile applications GUI testing based on testing‐as‐a‐service architecture is proposed. The proposed system performs all testing activities including automatic test case generation and simultaneous test execution on multiple virtual nodes for testing Android‐based applications. The proposed system reduces testing time and meets fast time‐to market constraint of mobile applications. Moreover, the proposed system architecture addresses many issues such as maximizing resource utilization, continuous monitoring to ensure system reliability, and applying fault‐tolerance approach to handle occurrence of any failure.