Pub Date : 2021-01-01DOI: 10.4018/IJOSSP.2021010104
A. Almulihi, Fahd S. Alharithi, Seifeddine Mechti, Roobaea Alroobaea, S. Rubaiee
People suspected of having COVID-19 need to know quickly if they are infected, so that they can isolate themselves, receive treatment, and inform those with whom they have been in close contact. Currently, the formal diagnosis of COVID-19 infection requires laboratory analysis of blood samples or swabs from the throat and nose. The lab test requires specialized equipment and takes at least 24 hours to produce a result. For this reason, in this paper, the authors tackle the problem of the detection of COVID-19 by developing an open source software to analyze chest x-ray thorax images. The method is based on supervised learning applied to 5000 images. However, deep learning techniques such as convolutional neural network (CNN) and mask R-CNN gives good results comparing with classic medical imaging. Using a dynamic learning rate, they obtained 0.96 accuracy for the training phase and 0.82 for the test. The results of our free tool are comparable to the best state of the art open source systems.
{"title":"A Software for Thorax Images Analysis Based on Deep Learning","authors":"A. Almulihi, Fahd S. Alharithi, Seifeddine Mechti, Roobaea Alroobaea, S. Rubaiee","doi":"10.4018/IJOSSP.2021010104","DOIUrl":"https://doi.org/10.4018/IJOSSP.2021010104","url":null,"abstract":"People suspected of having COVID-19 need to know quickly if they are infected, so that they can isolate themselves, receive treatment, and inform those with whom they have been in close contact. Currently, the formal diagnosis of COVID-19 infection requires laboratory analysis of blood samples or swabs from the throat and nose. The lab test requires specialized equipment and takes at least 24 hours to produce a result. For this reason, in this paper, the authors tackle the problem of the detection of COVID-19 by developing an open source software to analyze chest x-ray thorax images. The method is based on supervised learning applied to 5000 images. However, deep learning techniques such as convolutional neural network (CNN) and mask R-CNN gives good results comparing with classic medical imaging. Using a dynamic learning rate, they obtained 0.96 accuracy for the training phase and 0.82 for the test. The results of our free tool are comparable to the best state of the art open source systems.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"50 1","pages":"60-71"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79820603","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 : 2020-07-01DOI: 10.4018/ijossp.2020070101
D. K. Santhosh Kumar, Demain Antony DMello
Information extraction and analysis from the enormous graph data is expanding rapidly. From the survey, it is observed that 80% of researchers spend more than 40% of their project time in data cleaning. This signifies a huge need for data cleaning. Due to the characteristics of big data, the storage and retrieval is another major concern and is addressed by data indexing. The existing data cleaning techniques try to clean the graph data based on information like structural attributes and event log sequences. The cleaning of graph data on a single piece of information alone will not increase the performance of computation. Along with node, the label can also be inconsistent, so it is highly desirable to clean both to improve the performance. This paper addresses aforesaid issue by proposing graph data cleaning algorithm to detect the unstructured information along with inconsistent labeling and clean the data by applying rules and verify based on data inconsistency. The authors propose an indexing algorithm based on CSS-tree to build an efficient and scalable graph indexing on top of Hadoop.
{"title":"Efficient Algorithms for Cleaning and Indexing of Graph data","authors":"D. K. Santhosh Kumar, Demain Antony DMello","doi":"10.4018/ijossp.2020070101","DOIUrl":"https://doi.org/10.4018/ijossp.2020070101","url":null,"abstract":"Information extraction and analysis from the enormous graph data is expanding rapidly. From the survey, it is observed that 80% of researchers spend more than 40% of their project time in data cleaning. This signifies a huge need for data cleaning. Due to the characteristics of big data, the storage and retrieval is another major concern and is addressed by data indexing. The existing data cleaning techniques try to clean the graph data based on information like structural attributes and event log sequences. The cleaning of graph data on a single piece of information alone will not increase the performance of computation. Along with node, the label can also be inconsistent, so it is highly desirable to clean both to improve the performance. This paper addresses aforesaid issue by proposing graph data cleaning algorithm to detect the unstructured information along with inconsistent labeling and clean the data by applying rules and verify based on data inconsistency. The authors propose an indexing algorithm based on CSS-tree to build an efficient and scalable graph indexing on top of Hadoop.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"33 1","pages":"1-19"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82343587","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 : 2020-07-01DOI: 10.4018/ijossp.2020070103
S. R. M. Sekhar, G. Siddesh, S. Manvi
Identification and analysis of protein play a vital role in drug design and disease prediction. There are several open-source applications that have been developed for identifying essential proteins which are based on biological or topological features. These techniques infer the possibility of proteins to be essential by using the network topology and feature selection, which can ignore some of the features to reduce the complexity and, subsequently, results in less accuracy. In the paper, the authors have used selenium driver to scrap the dataset. Later, the authors integrated the chi-square method with support vector machine for the prediction of essential proteins in baker yeast. Here, chi-square is a test of dissimilarity used for altering the record, and afterward, the support vector machine is used to classify the test dataset. The results show that the proposed model Chi-SVM model achieves an accuracy of 99.56%, whereas BC and CC achieved an accuracy of 84.0% and 86.0%. Finally, the proposed model is validated using Statistical performance measures such as PPA, NPA, SA, and STA.
{"title":"Open-Source Essential Protein Prediction Model by Integrating Chi-Square and Support Vector Machine","authors":"S. R. M. Sekhar, G. Siddesh, S. Manvi","doi":"10.4018/ijossp.2020070103","DOIUrl":"https://doi.org/10.4018/ijossp.2020070103","url":null,"abstract":"Identification and analysis of protein play a vital role in drug design and disease prediction. There are several open-source applications that have been developed for identifying essential proteins which are based on biological or topological features. These techniques infer the possibility of proteins to be essential by using the network topology and feature selection, which can ignore some of the features to reduce the complexity and, subsequently, results in less accuracy. In the paper, the authors have used selenium driver to scrap the dataset. Later, the authors integrated the chi-square method with support vector machine for the prediction of essential proteins in baker yeast. Here, chi-square is a test of dissimilarity used for altering the record, and afterward, the support vector machine is used to classify the test dataset. The results show that the proposed model Chi-SVM model achieves an accuracy of 99.56%, whereas BC and CC achieved an accuracy of 84.0% and 86.0%. Finally, the proposed model is validated using Statistical performance measures such as PPA, NPA, SA, and STA.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"5 1","pages":"38-56"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87901340","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 : 2020-04-01DOI: 10.4018/ijossp.2020040103
Wasiur Rhmann, Gufran Ahmad Ansari
Software engineering repositories have been attracted by researchers to mine useful information about the different quality attributes of the software. These repositories have been helpful to software professionals to efficiently allocate various resources in the life cycle of software development. Software fault prediction is a quality assurance activity. In fault prediction, software faults are predicted before actual software testing. As exhaustive software testing is impossible, the use of software fault prediction models can help the proper allocation of testing resources. Various machine learning techniques have been applied to create software fault prediction models. In this study, ensemble models are used for software fault prediction. Change metrics-based data are collected for an open-source android project from GIT repository and code-based metrics data are obtained from PROMISE data repository and datasets kc1, kc2, cm1, and pc1 are used for experimental purpose. Results showed that ensemble models performed better compared to machine learning and hybrid search-based algorithms. Bagging ensemble was found to be more effective in the prediction of faults in comparison to soft and hard voting.
{"title":"Ensemble Techniques-Based Software Fault Prediction in an Open-Source Project","authors":"Wasiur Rhmann, Gufran Ahmad Ansari","doi":"10.4018/ijossp.2020040103","DOIUrl":"https://doi.org/10.4018/ijossp.2020040103","url":null,"abstract":"Software engineering repositories have been attracted by researchers to mine useful information about the different quality attributes of the software. These repositories have been helpful to software professionals to efficiently allocate various resources in the life cycle of software development. Software fault prediction is a quality assurance activity. In fault prediction, software faults are predicted before actual software testing. As exhaustive software testing is impossible, the use of software fault prediction models can help the proper allocation of testing resources. Various machine learning techniques have been applied to create software fault prediction models. In this study, ensemble models are used for software fault prediction. Change metrics-based data are collected for an open-source android project from GIT repository and code-based metrics data are obtained from PROMISE data repository and datasets kc1, kc2, cm1, and pc1 are used for experimental purpose. Results showed that ensemble models performed better compared to machine learning and hybrid search-based algorithms. Bagging ensemble was found to be more effective in the prediction of faults in comparison to soft and hard voting.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"104 1","pages":"33-48"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80815705","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 : 2020-04-01DOI: 10.4018/ijossp.2020040104
Amandeep Kaur, Sandeep Sharma, Munish Saini
Code clone refers to code snippets that are copied and pasted with or without modifications. In recent years, traditional approaches for clone detection combine with other domains for better detection of a clone. This paper discusses the systematic literature review of machine learning techniques used in code clone detection. This study provides insights into various tools and techniques developed for clone detection by implementing machine learning approaches and how effectively those tools and techniques to identify clones. The authors perform a systematic literature review on studies selected from popular computer science-related digital online databases from January 2004 to January 2020. The software system and datasets used for analyzing tools and techniques are mentioned. A neural network machine learning technique is primarily used for the identification of the clone. Clone detection based on a program dependency graph must be explored in the future because it carries semantic information of code fragments.
{"title":"Code Clone Detection Using Machine Learning Techniques: A Systematic Literature Review","authors":"Amandeep Kaur, Sandeep Sharma, Munish Saini","doi":"10.4018/ijossp.2020040104","DOIUrl":"https://doi.org/10.4018/ijossp.2020040104","url":null,"abstract":"Code clone refers to code snippets that are copied and pasted with or without modifications. In recent years, traditional approaches for clone detection combine with other domains for better detection of a clone. This paper discusses the systematic literature review of machine learning techniques used in code clone detection. This study provides insights into various tools and techniques developed for clone detection by implementing machine learning approaches and how effectively those tools and techniques to identify clones. The authors perform a systematic literature review on studies selected from popular computer science-related digital online databases from January 2004 to January 2020. The software system and datasets used for analyzing tools and techniques are mentioned. A neural network machine learning technique is primarily used for the identification of the clone. Clone detection based on a program dependency graph must be explored in the future because it carries semantic information of code fragments.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"269 1","pages":"49-75"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80467092","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 : 2020-04-01DOI: 10.4018/ijossp.2020040101
A. Hamdy, A. El-Laithy
When bug reports are submitted through bug tracking systems, they are analysed manually to identify their severity levels. A severity level specifies the negative impact of a bug on a system. With the huge number of submitted reports, setting the severity class manually is tedious and time consuming. Moreover, some bug types are reported more often than other types, which leads to imbalanced bug repositories. This paper proposes a multi-feature approach for automatic severity assignment, which leverages lexical, semantic, and categorical properties of the bug reports. The proposed approach utilizes word embeddings, topic model, vector space model, and an adapted K-Nearest Neighbour technique. Moreover, the impact of utilizing two sampling techniques, namely SMOTE and cluster-based under-sampling (CBU), were investigated. Experiments over two open source repositories, Eclipse and Mozilla, demonstrated that the proposed approach is superior to two previous studies.
{"title":"Multi-Feature Approach for Bug Severity Assignment","authors":"A. Hamdy, A. El-Laithy","doi":"10.4018/ijossp.2020040101","DOIUrl":"https://doi.org/10.4018/ijossp.2020040101","url":null,"abstract":"When bug reports are submitted through bug tracking systems, they are analysed manually to identify their severity levels. A severity level specifies the negative impact of a bug on a system. With the huge number of submitted reports, setting the severity class manually is tedious and time consuming. Moreover, some bug types are reported more often than other types, which leads to imbalanced bug repositories. This paper proposes a multi-feature approach for automatic severity assignment, which leverages lexical, semantic, and categorical properties of the bug reports. The proposed approach utilizes word embeddings, topic model, vector space model, and an adapted K-Nearest Neighbour technique. Moreover, the impact of utilizing two sampling techniques, namely SMOTE and cluster-based under-sampling (CBU), were investigated. Experiments over two open source repositories, Eclipse and Mozilla, demonstrated that the proposed approach is superior to two previous studies.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"129 1","pages":"1-15"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77400756","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 : 2020-04-01DOI: 10.4018/ijossp.2020040102
Anushree Agrawal, R. K. Singh
Changeability is an important aspect of software maintenance and helps in better planning of development and testing resources. Early detection of change-prone entities is beneficial in terms of both time and money and helps to estimate and meet deadlines reliably. Co-change prediction identifies the affected entities when implementing a change in the software system. Recent researches recommend the use of revision history for the identification of co-changed artifacts. However, very few studies are available for investigation of the effect of history size and age on prediction results. This manuscript studies the effect of age of change history on co-change prediction results in software applications by varying the weightage of change commits with time. ROC analysis is done to study the accuracy of the proposed approach, and the results indicate that the older change commits have lower significance in deriving the changeability pattern. The derived change impact set will be useful for software practitioners in change implementation and selective regression testing.
{"title":"Mining Software Repositories for Revision Age-Based Co-Change Probability Prediction","authors":"Anushree Agrawal, R. K. Singh","doi":"10.4018/ijossp.2020040102","DOIUrl":"https://doi.org/10.4018/ijossp.2020040102","url":null,"abstract":"Changeability is an important aspect of software maintenance and helps in better planning of development and testing resources. Early detection of change-prone entities is beneficial in terms of both time and money and helps to estimate and meet deadlines reliably. Co-change prediction identifies the affected entities when implementing a change in the software system. Recent researches recommend the use of revision history for the identification of co-changed artifacts. However, very few studies are available for investigation of the effect of history size and age on prediction results. This manuscript studies the effect of age of change history on co-change prediction results in software applications by varying the weightage of change commits with time. ROC analysis is done to study the accuracy of the proposed approach, and the results indicate that the older change commits have lower significance in deriving the changeability pattern. The derived change impact set will be useful for software practitioners in change implementation and selective regression testing.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"361 1","pages":"16-32"},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82639012","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 : 2020-01-01DOI: 10.4018/ijossp.2020010102
A. Saifan, Ahmad Adnan Alzyoud
Android is an operating system source which offers flexibility and support for most mobile applications, and easy access to social networks. It is important to understand the complexity of design, development, implementation, and testing of Android apps. A number of challenges may be faced in testing android applications, including the lack of testing processes and methods, testing experts being unavailable, poor in-house testing environment, and time restrictions. Mutation testing is a fault-based testing technique, applied by generating mutants and running the application with these mutants to analyze the killed and equivalent mutants. We defined a set of mutation operators according to the features of android applications: apps with content sharing, apps with multimedia, apps with graphics, and apps with user location and maps. We identified 42 mutation operators. In addition, we implemented a new tool, “µ-Android,” which automatically generates mutants and retrieves results to prove the efficiency of the test cases and enable the new operators.
{"title":"Mutation Testing to Evaluate Android Applications","authors":"A. Saifan, Ahmad Adnan Alzyoud","doi":"10.4018/ijossp.2020010102","DOIUrl":"https://doi.org/10.4018/ijossp.2020010102","url":null,"abstract":"Android is an operating system source which offers flexibility and support for most mobile applications, and easy access to social networks. It is important to understand the complexity of design, development, implementation, and testing of Android apps. A number of challenges may be faced in testing android applications, including the lack of testing processes and methods, testing experts being unavailable, poor in-house testing environment, and time restrictions. Mutation testing is a fault-based testing technique, applied by generating mutants and running the application with these mutants to analyze the killed and equivalent mutants. We defined a set of mutation operators according to the features of android applications: apps with content sharing, apps with multimedia, apps with graphics, and apps with user location and maps. We identified 42 mutation operators. In addition, we implemented a new tool, “µ-Android,” which automatically generates mutants and retrieves results to prove the efficiency of the test cases and enable the new operators.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"70 1","pages":"23-40"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79723650","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 : 2020-01-01DOI: 10.4018/ijossp.2020010101
Karollay Giuliani Oliveira Valério, C. E. S. Silva, Sandra Miranda Neves
Effective risk management contributes to the success of the software development project. The goal of this work was to identify risk management gaps, perspectives, the evolution of the theme and the study trends, in software development projects, using systematic literature review as a method. For the bibliometric analysis, articles referring to the topic were selected in the period from 2010 to 2018. As tools of analysis, Citespace and VOS Viewer software were used, allowing a comparative evaluation between the articles, as well as the analysis of clusters. Beyond content analysis of articles found. Gaps were identified for performance; team involvement; attention to failures; identification of tools for decision-making; and business strategy. In turn, perspectives were determined for research trends, such as the close relationship between business strategy, risk management and new management models. The research can propose new strategies and perspectives for risk management in software development and show their importance to the academic and practical spheres, demonstrating that the themes are complementary and important in the current technological and innovation sector.
{"title":"Risk Management in Software Development Projects: Systematic Review of the State of the Art Literature","authors":"Karollay Giuliani Oliveira Valério, C. E. S. Silva, Sandra Miranda Neves","doi":"10.4018/ijossp.2020010101","DOIUrl":"https://doi.org/10.4018/ijossp.2020010101","url":null,"abstract":"Effective risk management contributes to the success of the software development project. The goal of this work was to identify risk management gaps, perspectives, the evolution of the theme and the study trends, in software development projects, using systematic literature review as a method. For the bibliometric analysis, articles referring to the topic were selected in the period from 2010 to 2018. As tools of analysis, Citespace and VOS Viewer software were used, allowing a comparative evaluation between the articles, as well as the analysis of clusters. Beyond content analysis of articles found. Gaps were identified for performance; team involvement; attention to failures; identification of tools for decision-making; and business strategy. In turn, perspectives were determined for research trends, such as the close relationship between business strategy, risk management and new management models. The research can propose new strategies and perspectives for risk management in software development and show their importance to the academic and practical spheres, demonstrating that the themes are complementary and important in the current technological and innovation sector.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"18 3","pages":"1-22"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72599504","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 : 2020-01-01DOI: 10.4018/ijossp.2020070102
Nayeem Ahmad Bhat, Sheikh Umar Farooq
Researchers have devised and implemented different bug prediction approaches that use different metrics to predict bugs in software modules. However, the focus of research has been on proposing new approaches/models to predict bugs rather than on validating performance of existing approaches. In this paper, the authors evaluate and validate the findings of an algorithm that predicts the bug proneness index (bug score) of the software classes/modules. The algorithm uses normalized marginal R square values of software metrics as weights to the normalized metrics to compute bug proneness index (bug score). The experiment was performed on Eclipse JDT Core and reports significant improvements in F-measure of their algorithm as compared to the multiple linear regression. The authors found that there was no improvement in F-measure of evaluated algorithm compared to multiple linear regression. The use of marginal R square values as weights to the metrics in linear functions in the evaluated model instead of regression coefficients had no performance boost compared to the multiple linear regression.
{"title":"Empirical Evaluation of Bug Proneness Index Algorithm","authors":"Nayeem Ahmad Bhat, Sheikh Umar Farooq","doi":"10.4018/ijossp.2020070102","DOIUrl":"https://doi.org/10.4018/ijossp.2020070102","url":null,"abstract":"Researchers have devised and implemented different bug prediction approaches that use different metrics to predict bugs in software modules. However, the focus of research has been on proposing new approaches/models to predict bugs rather than on validating performance of existing approaches. In this paper, the authors evaluate and validate the findings of an algorithm that predicts the bug proneness index (bug score) of the software classes/modules. The algorithm uses normalized marginal R square values of software metrics as weights to the normalized metrics to compute bug proneness index (bug score). The experiment was performed on Eclipse JDT Core and reports significant improvements in F-measure of their algorithm as compared to the multiple linear regression. The authors found that there was no improvement in F-measure of evaluated algorithm compared to multiple linear regression. The use of marginal R square values as weights to the metrics in linear functions in the evaluated model instead of regression coefficients had no performance boost compared to the multiple linear regression.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"75 1","pages":"20-37"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79244778","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：