Pub Date : 2022-02-21DOI: 10.15282/ijsecs.8.1.2022.3.0093
Anthony Wambua Wambua, B. Maake
Given the increased reliance on technology, Software Quality Assurance(SQA) has become a vital area in Software Engineering (SE). SQA practices require training, cost and often take more time than actual code writing. Owing to these requirements, software developers often ignore or partly implement SQA practices, leading to potentially poor quality software development. The goal of the study is to characterise SQA practices of software developers in Kenya. As such, quantitative empirical research was conducted. Seventy-seven (N=77) completed questionnaires were received and analysed to yield the required insights. The analysis of the findings indicates compliance with SQA practices. However, the research unearths concerns such as failure to comply with Software Development Life Cycle (SDLC) models as having the potential to lower the quality of software products. The assessment found that Unit testing was the most common type of software test. Based on the findings and literature, recommendations are made. The need to improve software engineering education and invest in software testing is underscored. The results can be generalised to most developing countries and used by software developers and trainers to identify areas in SQA that need strengthening.
{"title":"CHARACTERIZING SOFTWARE QUALITY ASSURANCE PRACTICES IN KENYA","authors":"Anthony Wambua Wambua, B. Maake","doi":"10.15282/ijsecs.8.1.2022.3.0093","DOIUrl":"https://doi.org/10.15282/ijsecs.8.1.2022.3.0093","url":null,"abstract":"Given the increased reliance on technology, Software Quality Assurance(SQA) has become a vital area in Software Engineering (SE). SQA practices require training, cost and often take more time than actual code writing. Owing to these requirements, software developers often ignore or partly implement SQA practices, leading to potentially poor quality software development. The goal of the study is to characterise SQA practices of software developers in Kenya. As such, quantitative empirical research was conducted. Seventy-seven (N=77) completed questionnaires were received and analysed to yield the required insights. The analysis of the findings indicates compliance with SQA practices. However, the research unearths concerns such as failure to comply with Software Development Life Cycle (SDLC) models as having the potential to lower the quality of software products. The assessment found that Unit testing was the most common type of software test. Based on the findings and literature, recommendations are made. The need to improve software engineering education and invest in software testing is underscored. The results can be generalised to most developing countries and used by software developers and trainers to identify areas in SQA that need strengthening.","PeriodicalId":31240,"journal":{"name":"International Journal of Software Engineering and Computer Systems","volume":"55 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81213491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-16DOI: 10.15282/ijsecs.8.1.2022.2.0092
A. Abuhamdah, M. Al-Shabi
Fog computing has become a new trend in the Internet of things domain and cloud computing applications. It is a novel model to achieve the availability, flexibility and better responding time. In spite of that, there is so many challenges facing computing environments such as the misuse of the resources and load-balancing between them, which has a major effect on performance. The requirement of effective and robust load-balancing algorithms is one of the most significant interest in this field. Many researchers suggested various load-balancing algorithms in fog computing, but there is still inefficiency in the system performance and misalignment in load -balancing. This paper will provide a description of numerous concepts such as computing fog, fog nodes, load balancing and then we recommend a load-balancing algorithm to enhance the fog-computing environment performance, which is a hybrid algorithm benefits from the optimizing processing time (OPT) algorithms. In order to explore the proposed algorithm performance, a comparison made with other algorithms. Results indicates that using the proposed optimizing processing time algorithm in load-balancing algorithm has superior response and processing time than the compared algorithms to user requests, and the data total cost centre’s as well.
{"title":"HYBRID LOAD BALANCING ALGORITHM FOR FOG COMPUTING ENVIRONMENT","authors":"A. Abuhamdah, M. Al-Shabi","doi":"10.15282/ijsecs.8.1.2022.2.0092","DOIUrl":"https://doi.org/10.15282/ijsecs.8.1.2022.2.0092","url":null,"abstract":"Fog computing has become a new trend in the Internet of things domain and cloud computing applications. It is a novel model to achieve the availability, flexibility and better responding time. In spite of that, there is so many challenges facing computing environments such as the misuse of the resources and load-balancing between them, which has a major effect on performance. The requirement of effective and robust load-balancing algorithms is one of the most significant interest in this field. Many researchers suggested various load-balancing algorithms in fog computing, but there is still inefficiency in the system performance and misalignment in load -balancing. This paper will provide a description of numerous concepts such as computing fog, fog nodes, load balancing and then we recommend a load-balancing algorithm to enhance the fog-computing environment performance, which is a hybrid algorithm benefits from the optimizing processing time (OPT) algorithms. In order to explore the proposed algorithm performance, a comparison made with other algorithms. Results indicates that using the proposed optimizing processing time algorithm in load-balancing algorithm has superior response and processing time than the compared algorithms to user requests, and the data total cost centre’s as well.","PeriodicalId":31240,"journal":{"name":"International Journal of Software Engineering and Computer Systems","volume":"35 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90217416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Identical code fragments in different locations are recognized as code clones. There are four native terminologies of code clones concluded as Type-1, Type-2, Type-3 and Type-4. Code clones can be identified using various approaches and models. Generic Code Clone Detection (GCCD) model was created to detect all four terminologies of code clones through five processes. A prototype has been developed to detect code clones in Java programming language that starts with Pre-processing Transformation, Parameterization, Categorization and ends with the Match Detection process. Hence, this work targeted to enhance the prototype using a GCCD model to identify all clone types in Python language. Enhancements are done in the Pre-processing process and parameterization process of the GCCD model to fit the Python language criteria. Results are improved by finding the best constant value and suitable weightage according to Python language. Proposed enhancement results of the Python language clone detection in GCCD model imply that Public as the weightage indicator and def as the best constant value.
{"title":"ENHANCEMENT OF GENERIC CODE CLONE DETECTION MODEL FOR PYTHON APPLICATION","authors":"Ilyana Najwa Aiza Asmad, Al-Fahim Mubarak Ali, Nik Intan Syahiddatul Ilani Jailani","doi":"10.15282/ijsecs.8.1.2022.1.0092","DOIUrl":"https://doi.org/10.15282/ijsecs.8.1.2022.1.0092","url":null,"abstract":"Identical code fragments in different locations are recognized as code clones. There are four native terminologies of code clones concluded as Type-1, Type-2, Type-3 and Type-4. Code clones can be identified using various approaches and models. Generic Code Clone Detection (GCCD) model was created to detect all four terminologies of code clones through five processes. A prototype has been developed to detect code clones in Java programming language that starts with Pre-processing Transformation, Parameterization, Categorization and ends with the Match Detection process. Hence, this work targeted to enhance the prototype using a GCCD model to identify all clone types in Python language. Enhancements are done in the Pre-processing process and parameterization process of the GCCD model to fit the Python language criteria. Results are improved by finding the best constant value and suitable weightage according to Python language. Proposed enhancement results of the Python language clone detection in GCCD model imply that Public as the weightage indicator and def as the best constant value.","PeriodicalId":31240,"journal":{"name":"International Journal of Software Engineering and Computer Systems","volume":"235 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77148977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-24DOI: 10.15282/ijsecs.8.1.2022.6.0096
Oluwabukola Ayo-Bello, Abiodun Musa Aibinu, O. Ubadike, Adeiza James Onumanyi, Muyideen Omuya Momoh
Call Setup Time (CST) is one of the key performance indicators (KPIs) that Mobile Network Providers (MNPs) are mostly appertain. It has been established that long CST usually severely affects the user experience. Owing to the limitations associated with gleaning the CST data from MNPs, this paper provides the development of QoS estimation algorithm from various CST parameters. The algorithm involves the determination of CST; Inter-Burst time; Intra-Burst time and Call duration in time domain. The caller Frequency content was also determined by the application of fast Fourier Transform before computing the Mean Square Error (MSE). The eventual QoS rating is done after the computation of the MSE from various individual parameters. Four hourly data consisting of 10 sets each were collected three times in a week for four weeks for each MNP’s for creating Caller Ringtone dataset and testing the developed algorithm. Performance analysis of the system in accurately determining: CST; Intraburst time; Interburst time and Call durations were carried out. Results obtained shows that the proposed technique accurately computes these parameters and maximum error obtained was to the value of 10%. Furthermore, the QoS obtained shows an error margin of less than 5 % was observed when the developed technique was compared to the ground truth. Thus, the proposed algorithm was able to compute the QoS using Caller Ringtone only, thus independent of MNP.
{"title":"A QOS ESTIMATION ALGORITHM FROM CALLER RINGTONE ANALYSIS IN GSM NETWORK","authors":"Oluwabukola Ayo-Bello, Abiodun Musa Aibinu, O. Ubadike, Adeiza James Onumanyi, Muyideen Omuya Momoh","doi":"10.15282/ijsecs.8.1.2022.6.0096","DOIUrl":"https://doi.org/10.15282/ijsecs.8.1.2022.6.0096","url":null,"abstract":"Call Setup Time (CST) is one of the key performance indicators (KPIs) that Mobile Network Providers (MNPs) are mostly appertain. It has been established that long CST usually severely affects the user experience. Owing to the limitations associated with gleaning the CST data from MNPs, this paper provides the development of QoS estimation algorithm from various CST parameters. The algorithm involves the determination of CST; Inter-Burst time; Intra-Burst time and Call duration in time domain. The caller Frequency content was also determined by the application of fast Fourier Transform before computing the Mean Square Error (MSE). The eventual QoS rating is done after the computation of the MSE from various individual parameters. Four hourly data consisting of 10 sets each were collected three times in a week for four weeks for each MNP’s for creating Caller Ringtone dataset and testing the developed algorithm. Performance analysis of the system in accurately determining: CST; Intraburst time; Interburst time and Call durations were carried out. Results obtained shows that the proposed technique accurately computes these parameters and maximum error obtained was to the value of 10%. Furthermore, the QoS obtained shows an error margin of less than 5 % was observed when the developed technique was compared to the ground truth. Thus, the proposed algorithm was able to compute the QoS using Caller Ringtone only, thus independent of MNP.","PeriodicalId":31240,"journal":{"name":"International Journal of Software Engineering and Computer Systems","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74707284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-24DOI: 10.15282/ijsecs.8.1.2022.5.0095
Nuzhat Qadir, R. Ahmad
The security requirements are one of the non-functional requirements (NFR) which acts as a constraint on the functions of the system to be built. Security requirements are important and may affect the entire quality of the system. Unfortunately, many organizations do not pay much attention to it. The security problems should be focused on the early phases of the development process i.e. in the requirements phase to stop the problems spreading down in the later phases and in turn to avoid the rework. Subsequently, when security requirements are to be focused, proper guidance should be provided which should assist requirements engineers. Many security requirements engineering methods were developed in the past which require different level of expertise such as SQUARE process which requires requirements engineer to have a certain level of security expertise. Moreover, it lacks proper guidance especially for novice developers in applying the existing security requirements engineering (SecRE) methods to identify security requirements. Hence, this study intends to address the gap by developing a guided template to assist novice developers in the security requirements identification and documentation. The main objectives of the research are: 1) to study and investigate the existing security requirements engineering (SecRE) methods. 2) To develop a template to aid novice developers in identifying and documenting security requirements. The developed template is applied to two case studies of software projects to determine its usability and applicability. The results of the case studies evaluation show that both the usability and applicability of the template is good. The template is also evaluated by several experts and software practitioners. The evaluation results show that the SecRS template is found to be satisfying the usability and applicability factors; thereby confirming that the proposed template achieves its desired objective of aiding the novice developers to identify and document security requirements correctly.
{"title":"SECRS TEMPLATE TO AID NOVICE DEVELOPERS IN SECURITY REQUIREMENTS IDENTIFICATION AND DOCUMENTATION","authors":"Nuzhat Qadir, R. Ahmad","doi":"10.15282/ijsecs.8.1.2022.5.0095","DOIUrl":"https://doi.org/10.15282/ijsecs.8.1.2022.5.0095","url":null,"abstract":"The security requirements are one of the non-functional requirements (NFR) which acts as a constraint on the functions of the system to be built. Security requirements are important and may affect the entire quality of the system. Unfortunately, many organizations do not pay much attention to it. The security problems should be focused on the early phases of the development process i.e. in the requirements phase to stop the problems spreading down in the later phases and in turn to avoid the rework. Subsequently, when security requirements are to be focused, proper guidance should be provided which should assist requirements engineers. Many security requirements engineering methods were developed in the past which require different level of expertise such as SQUARE process which requires requirements engineer to have a certain level of security expertise. Moreover, it lacks proper guidance especially for novice developers in applying the existing security requirements engineering (SecRE) methods to identify security requirements. Hence, this study intends to address the gap by developing a guided template to assist novice developers in the security requirements identification and documentation. The main objectives of the research are: 1) to study and investigate the existing security requirements engineering (SecRE) methods. 2) To develop a template to aid novice developers in identifying and documenting security requirements. The developed template is applied to two case studies of software projects to determine its usability and applicability. The results of the case studies evaluation show that both the usability and applicability of the template is good. The template is also evaluated by several experts and software practitioners. The evaluation results show that the SecRS template is found to be satisfying the usability and applicability factors; thereby confirming that the proposed template achieves its desired objective of aiding the novice developers to identify and document security requirements correctly.","PeriodicalId":31240,"journal":{"name":"International Journal of Software Engineering and Computer Systems","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75316331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-21DOI: 10.15282/ijsecs.7.2.2021.6.0089
D. Aliu, M. O. Momoh
Researchers are yet to entirely mapped out the difficulty in allocating optimal resources to mobile Worldwide Interoperability for Microwave Access (WiMAX) subscribers. This research presents an optimal scheduling algorithm for WiMAX resource allocation based on an Particle Swarm Optimization (PSO). In this work, sub-group creation is used to offer a PSO-based technique for allocating subcarriers and Orthogonal Frequency Division Multiplexing (OFDM) symbols to mobile WiMAX customers. The WiMAX network environment is organized into seven layers, with seven different modulation and coding algorithms proposed for sending packets to subscribers within each layer. By adopting an improved PSO-based WiMAX resource allocation method, an enhanced model for throughput maximization and channel data rate was implemented. The Aggregate Data Rate (ADR) and Channel Data Rate (CDR) for each scenario were obtained by simulating several scenarios of WiMAX multicast service to mobile users. Based on the performance evaluation of the enhanced algorithm for ADR and CDR, the results for the various layers and uniform distribution of users over the full layers were 350Mbps, 525Mbps, 700Mbps, 1050Mbps, 1050Mbps, 1400Mbps, 1575Mbps, and 1398Mbps. 6.98Mbps, 10.48Mbps, 13.97Mbps, 20.95Mbps, 20.95Mbps, 27.94Mbps, 31.5Mbps, and 28Mbps were also achieved for CDR. The significance of optimal resource allocation is to achieved a maximum ADR and CDR. The results showed a fair distribution of resources within the coverage area of the network .
{"title":"OPTIMAL RESOURCE SCHEDULING ALGORITHM FOR OFDMA-BASED MULTICAST TRAFFIC DELIVERY OVER WIMAX NETWORKS USING PARTICLE SWARM OPTIMIZATION","authors":"D. Aliu, M. O. Momoh","doi":"10.15282/ijsecs.7.2.2021.6.0089","DOIUrl":"https://doi.org/10.15282/ijsecs.7.2.2021.6.0089","url":null,"abstract":"Researchers are yet to entirely mapped out the difficulty in allocating optimal resources to mobile Worldwide Interoperability for Microwave Access (WiMAX) subscribers. This research presents an optimal scheduling algorithm for WiMAX resource allocation based on an Particle Swarm Optimization (PSO). In this work, sub-group creation is used to offer a PSO-based technique for allocating subcarriers and Orthogonal Frequency Division Multiplexing (OFDM) symbols to mobile WiMAX customers. The WiMAX network environment is organized into seven layers, with seven different modulation and coding algorithms proposed for sending packets to subscribers within each layer. By adopting an improved PSO-based WiMAX resource allocation method, an enhanced model for throughput maximization and channel data rate was implemented. The Aggregate Data Rate (ADR) and Channel Data Rate (CDR) for each scenario were obtained by simulating several scenarios of WiMAX multicast service to mobile users. Based on the performance evaluation of the enhanced algorithm for ADR and CDR, the results for the various layers and uniform distribution of users over the full layers were 350Mbps, 525Mbps, 700Mbps, 1050Mbps, 1050Mbps, 1400Mbps, 1575Mbps, and 1398Mbps. 6.98Mbps, 10.48Mbps, 13.97Mbps, 20.95Mbps, 20.95Mbps, 27.94Mbps, 31.5Mbps, and 28Mbps were also achieved for CDR. The significance of optimal resource allocation is to achieved a maximum ADR and CDR. The results showed a fair distribution of resources within the coverage area of the network .","PeriodicalId":31240,"journal":{"name":"International Journal of Software Engineering and Computer Systems","volume":"15 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82124529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-21DOI: 10.15282/ijsecs.7.2.2021.7.0090
Hayder Ghazi Alwattar
Data mining classification models are developed and investigated in this paper. These models are adopted to develop and redesign several business processes based on post-operative data. Post-operative data were collected and used via the Waikato Environment for Knowledge Analysis (WEKA), to investigate the factors influencing patients’ admission after surgery and compare the developed DM classification models. The results reveal that each implemented DM technique entails different attributes affecting patients’ post-surgery admission status. The comparison suggests that neural networks outperform other classification techniques. Further, the optimal number of beds required to accommodate post-operative patients is investigated. The simulation was conducted using queuing theory software to compute the expected number of beds required to achieve zero waiting time. The results indicate that the number of beds required to accommodate post-surgery patients waiting in the queue is the length of 1, which means that one bed will be available due to patient discharge.
本文对数据挖掘分类模型进行了开发和研究。采用这些模型来开发和重新设计基于术后数据的几个业务流程。通过Waikato Environment for Knowledge Analysis (WEKA)收集术后数据，探讨影响患者术后入院的因素，并比较已建立的糖尿病分类模型。结果表明，每种实施的DM技术都包含不同的属性，影响患者术后入院状态。比较表明，神经网络优于其他分类技术。此外，研究了容纳术后患者所需的最佳床位数量。利用排队理论软件进行仿真，计算达到零等待时间所需的期望床位数量。结果表明，等待队列的术后患者所需床位数为1，即由于患者出院，将有1张床位可用。
{"title":"REDESIGNING POST-OPERATIVE PROCESSES USING DATA MINING CLASSIFICATION TECHNIQUES","authors":"Hayder Ghazi Alwattar","doi":"10.15282/ijsecs.7.2.2021.7.0090","DOIUrl":"https://doi.org/10.15282/ijsecs.7.2.2021.7.0090","url":null,"abstract":"Data mining classification models are developed and investigated in this paper. These models are adopted to develop and redesign several business processes based on post-operative data. Post-operative data were collected and used via the Waikato Environment for Knowledge Analysis (WEKA), to investigate the factors influencing patients’ admission after surgery and compare the developed DM classification models. The results reveal that each implemented DM technique entails different attributes affecting patients’ post-surgery admission status. The comparison suggests that neural networks outperform other classification techniques. Further, the optimal number of beds required to accommodate post-operative patients is investigated. The simulation was conducted using queuing theory software to compute the expected number of beds required to achieve zero waiting time. The results indicate that the number of beds required to accommodate post-surgery patients waiting in the queue is the length of 1, which means that one bed will be available due to patient discharge.","PeriodicalId":31240,"journal":{"name":"International Journal of Software Engineering and Computer Systems","volume":"45 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91033506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-11DOI: 10.15282/ijsecs.7.2.2021.5.0088
Oyelakin A. M, Alimi O. M, Mustapha I. O, Ajiboye I. K
Phishing attacks have been used in different ways to harvest the confidential information of unsuspecting internet users. To stem the tide of phishing-based attacks, several machine learning techniques have been proposed in the past. However, fewer studies have considered investigating single and ensemble machine learning-based models for the classification of phishing attacks. This study carried out performance analysis of selected single and ensemble machine learning (ML) classifiers in phishing classification.The focus is to investigate how these algorithms behave in the classification of phishing attacks in the chosen dataset. Logistic Regression and Decision Trees were chosen as single learning classifiers while simple voting techniques and Random Forest were used as the ensemble machine learning algorithms. Accuracy, Precision, Recall and F1-score were used as performance metrics. Logistic Regression algorithm recorded 0.86 as accuracy, 0.89 as precision, 0.87 as recall and 0.81 as F1-score. Similarly, the Decision Trees classifier achieved an accuracy of 0.87, 0.83 for precision, 0.88 for recall and 0.81 for F1-score. In the voting ensemble, accuracy of 0.92 was achieved. 0.90 was obtained for precision, 0.92 for recall and 0.92 for F1-score. Random Forest algorithm recorded 0.98, 0.97, 0.98 and 0.97 as accuracy, precision, recall and F1-score respectively. From the experimental analyses, Random Forest algorithm outperformed simple averaging classifier and the two single algorithms used for phishing url detection. The study established that the ensemble techniques that were used for the experimentations are more efficient for phishing url identification compared to the single classifiers.
{"title":"ANALYSIS OF SINGLE AND ENSEMBLE MACHINE LEARNING CLASSIFIERS FOR PHISHING ATTACKS DETECTION","authors":"Oyelakin A. M, Alimi O. M, Mustapha I. O, Ajiboye I. K","doi":"10.15282/ijsecs.7.2.2021.5.0088","DOIUrl":"https://doi.org/10.15282/ijsecs.7.2.2021.5.0088","url":null,"abstract":"Phishing attacks have been used in different ways to harvest the confidential information of unsuspecting internet users. To stem the tide of phishing-based attacks, several machine learning techniques have been proposed in the past. However, fewer studies have considered investigating single and ensemble machine learning-based models for the classification of phishing attacks. This study carried out performance analysis of selected single and ensemble machine learning (ML) classifiers in phishing classification.The focus is to investigate how these algorithms behave in the classification of phishing attacks in the chosen dataset. Logistic Regression and Decision Trees were chosen as single learning classifiers while simple voting techniques and Random Forest were used as the ensemble machine learning algorithms. Accuracy, Precision, Recall and F1-score were used as performance metrics. Logistic Regression algorithm recorded 0.86 as accuracy, 0.89 as precision, 0.87 as recall and 0.81 as F1-score. Similarly, the Decision Trees classifier achieved an accuracy of 0.87, 0.83 for precision, 0.88 for recall and 0.81 for F1-score. In the voting ensemble, accuracy of 0.92 was achieved. 0.90 was obtained for precision, 0.92 for recall and 0.92 for F1-score. Random Forest algorithm recorded 0.98, 0.97, 0.98 and 0.97 as accuracy, precision, recall and F1-score respectively. From the experimental analyses, Random Forest algorithm outperformed simple averaging classifier and the two single algorithms used for phishing url detection. The study established that the ensemble techniques that were used for the experimentations are more efficient for phishing url identification compared to the single classifiers.\u0000 ","PeriodicalId":31240,"journal":{"name":"International Journal of Software Engineering and Computer Systems","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86726947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-08DOI: 10.15282/ijsecs.7.2.2021.4.0087
Ghada M. Alqubati, Ghaleb H. Algaphari
Alzheimer’s disease (AD) is a progressive neurodegenerative disorder. It can cause a massive impact on a patient's memory and mobility. As this disease is irreversible, early diagnosis is crucial for delaying the symptoms and adjusting the patient's lifestyle. Many machine learning (ML) and deep learning (DL) based-approaches have been proposed to accurately predict AD before its symptoms onset. However, finding the most effective approach for AD early prediction is still challenging. This review explored 24 papers published from 2018 until 2021. These papers have proposed different approaches using state of the art machine learning and deep learning algorithms on different biomarkers to early detect AD. The review explored them from different perspectives to derive potential research gaps and draw conclusions and recommendations. It classified these recent approaches in terms of the learning technique used and AD biomarkers. It summarized and compared their findings, and defined their strengths and limitations. It also provided a summary of the common AD biomarkers. From this review, it was found that some approaches strove to increase the prediction accuracy regardless of their complexity such as using heterogeneous datasets, while others sought to find the most practical and affordable ways to predict the disease and yet achieve good accuracy such as using audio data. It was also noticed that DL based-approaches with image biomarkers remarkably surpassed ML based-approaches. However, they achieved poorly with genetic variants data. Despite the great importance of genetic variants biomarkers, their large variance and complexity could lead to a complex approach or poor accuracy. These data are crucial to discover the underlying structure of AD and detect it at early stages. However, an effective pre-processing approach is still needed to refine these data and employ them efficiently using the powerful DL algorithms.
{"title":"MACHINE LEARNING AND DEEP LEARNING-BASED APPROACHES ON VARIOUS BIOMARKERS FOR ALZHEIMER’S DISEASE EARLY DETECTION: A REVIEW","authors":"Ghada M. Alqubati, Ghaleb H. Algaphari","doi":"10.15282/ijsecs.7.2.2021.4.0087","DOIUrl":"https://doi.org/10.15282/ijsecs.7.2.2021.4.0087","url":null,"abstract":"Alzheimer’s disease (AD) is a progressive neurodegenerative disorder. It can cause a massive impact on a patient's memory and mobility. As this disease is irreversible, early diagnosis is crucial for delaying the symptoms and adjusting the patient's lifestyle. Many machine learning (ML) and deep learning (DL) based-approaches have been proposed to accurately predict AD before its symptoms onset. However, finding the most effective approach for AD early prediction is still challenging. This review explored 24 papers published from 2018 until 2021. These papers have proposed different approaches using state of the art machine learning and deep learning algorithms on different biomarkers to early detect AD. The review explored them from different perspectives to derive potential research gaps and draw conclusions and recommendations. It classified these recent approaches in terms of the learning technique used and AD biomarkers. It summarized and compared their findings, and defined their strengths and limitations. It also provided a summary of the common AD biomarkers. From this review, it was found that some approaches strove to increase the prediction accuracy regardless of their complexity such as using heterogeneous datasets, while others sought to find the most practical and affordable ways to predict the disease and yet achieve good accuracy such as using audio data. It was also noticed that DL based-approaches with image biomarkers remarkably surpassed ML based-approaches. However, they achieved poorly with genetic variants data. Despite the great importance of genetic variants biomarkers, their large variance and complexity could lead to a complex approach or poor accuracy. These data are crucial to discover the underlying structure of AD and detect it at early stages. However, an effective pre-processing approach is still needed to refine these data and employ them efficiently using the powerful DL algorithms.","PeriodicalId":31240,"journal":{"name":"International Journal of Software Engineering and Computer Systems","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85176671","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-30DOI: 10.15282/ijsecs.7.2.2021.3.0086
M. O. Momoh, P. Chinedu, W. Nwankwo, D. Aliu, M.S. Shaba
In recent times, more scholastic and social attention have been paid to blockchain and its distributed ledger system mechanism. The reasons for this ever-increasing attention cannot be far-fetched: blockchain now occupies a copious position in the present-day ways of doing things economically, digitally and ‘digital-socially’. Blockchain could be described as a distributed ledger system that allows secure transactions without a central management system. In this distributed ledger system, transactions are coded into blocks, which are linked to each other in the form of a chain. The first application of blockchain is in the bitcoin cryptocurrency. Though not limited to bitcoin, blockchain finds usefulness in security and trusts for instance, digital assets could be coded into blocks to ensure and enforce quality of trust. Consequent upon the quality of trust the blockchain confers on a digital asset, transparency among participating nodes is guaranteed. This is because, any change made to any record in a given block automatically initiates and enforces a corresponding change in all other blocks in the chain hence tampering or breach is almost impossible. Owing to its impressive prospects in the socioeconomic and political ecosystem, this paper was conceived to examine the current developments around this novel technology with particular emphasis on its benefits and proposed challenges and needs to fill the gap created in the vital socioeconomic domains. The paper concludes that the blockchain technology is a plausible approach to restoring the trust, confidentiality, availability and integrity in transactions in the cyberspace and the world at large as majority of the global economy thrives in the cloud.
{"title":"BLOCKCHAIN ADOPTION: APPLICATIONS AND CHALLENGES","authors":"M. O. Momoh, P. Chinedu, W. Nwankwo, D. Aliu, M.S. Shaba","doi":"10.15282/ijsecs.7.2.2021.3.0086","DOIUrl":"https://doi.org/10.15282/ijsecs.7.2.2021.3.0086","url":null,"abstract":"In recent times, more scholastic and social attention have been paid to blockchain and its distributed ledger system mechanism. The reasons for this ever-increasing attention cannot be far-fetched: blockchain now occupies a copious position in the present-day ways of doing things economically, digitally and ‘digital-socially’. Blockchain could be described as a distributed ledger system that allows secure transactions without a central management system. In this distributed ledger system, transactions are coded into blocks, which are linked to each other in the form of a chain. The first application of blockchain is in the bitcoin cryptocurrency. Though not limited to bitcoin, blockchain finds usefulness in security and trusts for instance, digital assets could be coded into blocks to ensure and enforce quality of trust. Consequent upon the quality of trust the blockchain confers on a digital asset, transparency among participating nodes is guaranteed. This is because, any change made to any record in a given block automatically initiates and enforces a corresponding change in all other blocks in the chain hence tampering or breach is almost impossible. Owing to its impressive prospects in the socioeconomic and political ecosystem, this paper was conceived to examine the current developments around this novel technology with particular emphasis on its benefits and proposed challenges and needs to fill the gap created in the vital socioeconomic domains. The paper concludes that the blockchain technology is a plausible approach to restoring the trust, confidentiality, availability and integrity in transactions in the cyberspace and the world at large as majority of the global economy thrives in the cloud.","PeriodicalId":31240,"journal":{"name":"International Journal of Software Engineering and Computer Systems","volume":"42 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85123103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：