Software quality assessment is an important subject among the researchers in the software development domain. The quality assessment is generally done either at the design level through some of the design attributes or through code when the product is ready. These two types of software quality are referred to as design quality and product quality, respectively. Several techniques and tools are available that facilitate to assess the design as well as the product quality of software. In this paper, a neural network model is proposed for the assessment of quality of object-oriented software at the product level. The authors select a subset of existing object-oriented metrics that are normalized at three levels and used to find quality factors like understandability, reusability, flexibility, maintainability, reliability, extensibility, and modifiability for the model development. The model is validated by assessing quality levels of 33 open source object-oriented software of different design complexities and observing a high correlation between these quality levels in comparison with an existing model.
{"title":"Neural Network-Based Model for the Quality Assessment of Object-Oriented Software","authors":"Sumit Babu, Raghuraj Singh","doi":"10.4018/ijossp.313182","DOIUrl":"https://doi.org/10.4018/ijossp.313182","url":null,"abstract":"Software quality assessment is an important subject among the researchers in the software development domain. The quality assessment is generally done either at the design level through some of the design attributes or through code when the product is ready. These two types of software quality are referred to as design quality and product quality, respectively. Several techniques and tools are available that facilitate to assess the design as well as the product quality of software. In this paper, a neural network model is proposed for the assessment of quality of object-oriented software at the product level. The authors select a subset of existing object-oriented metrics that are normalized at three levels and used to find quality factors like understandability, reusability, flexibility, maintainability, reliability, extensibility, and modifiability for the model development. The model is validated by assessing quality levels of 33 open source object-oriented software of different design complexities and observing a high correlation between these quality levels in comparison with an existing model.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91057713","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}
Mainly in the present times, the description of the services and their working procedure have been established in natural text language. We have obtained service groups based on their similarities to reduce search space and time in service innovation. Major topic models such as LSA, LDA, and CTM policies have not been able to show effective performance due to the short description and limited description of services in text form, the reduction or absence of words that occur. To solve the issues created by brief text, the Dirichlet Multinomial Mixer model (DMM) with features representation using the Gibbs algorithm has been developed to reduce dimensionality in clustering and enhance performance. The launch results prove that DMM-Gibbs can give better results than all other methods with agglomerative or K-means clustering methods by sampling. Evaluations with internal and external criteria were used to calculate clustering performance based on these two values. Using this standard model, the dimensionality can be reduced to 93.13% and better clustering performance can be achieved.
{"title":"Enhancing Clustering Performance Using Topic Modeling-Based Dimensionality Reduction","authors":"T. Ramathulasi, M. Babu","doi":"10.4018/ijossp.300755","DOIUrl":"https://doi.org/10.4018/ijossp.300755","url":null,"abstract":"Mainly in the present times, the description of the services and their working procedure have been established in natural text language. We have obtained service groups based on their similarities to reduce search space and time in service innovation. Major topic models such as LSA, LDA, and CTM policies have not been able to show effective performance due to the short description and limited description of services in text form, the reduction or absence of words that occur. To solve the issues created by brief text, the Dirichlet Multinomial Mixer model (DMM) with features representation using the Gibbs algorithm has been developed to reduce dimensionality in clustering and enhance performance. The launch results prove that DMM-Gibbs can give better results than all other methods with agglomerative or K-means clustering methods by sampling. Evaluations with internal and external criteria were used to calculate clustering performance based on these two values. Using this standard model, the dimensionality can be reduced to 93.13% and better clustering performance can be achieved.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"23 1","pages":"1-16"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76830433","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}
Context: The technology of machine learning and data science is gradually evolving and improving. In this process, we feel the importance of data science to solve a problem. Objective: In this article our main objective is to predict the customer churn, i.e. whether the customer will leave the telecom service or they will continue with the service. In this paper, we have also followed some statistical measures like we have computed the mean, standard deviation, min, max, 25%, 50%, 75% values of the data. Mean is the average value of the data values. The standard deviation is a measure of the amount of variation or dispersion of a set of values. Conclusion: We have done an extensive data pre-processing and built Machine Learning models, and found out that among all the models Logistic regression gives the best performance i.e 81.5%., and hence we chose that as our final model to indicates the churn prediction
{"title":"Will the Customer survive or not in the organization ? A Perspective of churn Prediction using Supervised Learning","authors":"","doi":"10.4018/ijossp.300753","DOIUrl":"https://doi.org/10.4018/ijossp.300753","url":null,"abstract":"Context: The technology of machine learning and data science is gradually evolving and improving. In this process, we feel the importance of data science to solve a problem. Objective: In this article our main objective is to predict the customer churn, i.e. whether the customer will leave the telecom service or they will continue with the service. In this paper, we have also followed some statistical measures like we have computed the mean, standard deviation, min, max, 25%, 50%, 75% values of the data. Mean is the average value of the data values. The standard deviation is a measure of the amount of variation or dispersion of a set of values. Conclusion: We have done an extensive data pre-processing and built Machine Learning models, and found out that among all the models Logistic regression gives the best performance i.e 81.5%., and hence we chose that as our final model to indicates the churn prediction","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"42 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86630706","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}
The aim of present research is to examine the influence of identified factors on efficacy of electronic word-of-mouth (e-WOM) for selected e-retailers on social media platform Twitter, applying data mining technique through python software programming. Taking the use of different programming and context as a research gap, the relationship among three important factors viz; network related, text related and time related factors and their influence on e-WOM has been examined on randomly tracked 2582 tweets about two of the reputed Indian e-retailers, Snapdeal and Flipkart. This study may be of immense help to e-retailers in identifying their reference customers (influential customers) on social media platform which in turn may be channelized for the purpose of viral marketing and other communication campaigns.
{"title":"Identifying Factors Influencing E-WOM on Social Networking Sites","authors":"Noopur Agrawal, A. Tripathi, Priti Jagwani","doi":"10.4018/ijossp.311838","DOIUrl":"https://doi.org/10.4018/ijossp.311838","url":null,"abstract":"The aim of present research is to examine the influence of identified factors on efficacy of electronic word-of-mouth (e-WOM) for selected e-retailers on social media platform Twitter, applying data mining technique through python software programming. Taking the use of different programming and context as a research gap, the relationship among three important factors viz; network related, text related and time related factors and their influence on e-WOM has been examined on randomly tracked 2582 tweets about two of the reputed Indian e-retailers, Snapdeal and Flipkart. This study may be of immense help to e-retailers in identifying their reference customers (influential customers) on social media platform which in turn may be channelized for the purpose of viral marketing and other communication campaigns.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82120228","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}
Tracking changes in code using revision history shared by collaborative teams during software evolution improves traceability. Existing techniques provides incomplete and inaccurate revision history due to lack in detection of renaming and shifting at file, class, and method granularities simultaneously. This research analyzes and prioritizes the metrics responsible for detecting such changes and update the revision history. This improves the traceability by tracking complete and accurate revision history that further improves the processes related to mining software repositories. It proposes SBFSelector algorithm that uses Jaccard Similarity and cosine similarity based on the prioritized metrics to identify these changes. Result shows that 73% metrics belongs to size and complexity that holds more significance over remaining categories. Random forest is best classifier for tracking changes with 0.99 true positive rate and 0.01 false positive rate. It improves traceability by increasing the Kappa statistic and true positive rate as compared to Understand tool.
{"title":"SBFSelector","authors":"Ritu Garg, R. K. Singh","doi":"10.4018/ijossp.311839","DOIUrl":"https://doi.org/10.4018/ijossp.311839","url":null,"abstract":"Tracking changes in code using revision history shared by collaborative teams during software evolution improves traceability. Existing techniques provides incomplete and inaccurate revision history due to lack in detection of renaming and shifting at file, class, and method granularities simultaneously. This research analyzes and prioritizes the metrics responsible for detecting such changes and update the revision history. This improves the traceability by tracking complete and accurate revision history that further improves the processes related to mining software repositories. It proposes SBFSelector algorithm that uses Jaccard Similarity and cosine similarity based on the prioritized metrics to identify these changes. Result shows that 73% metrics belongs to size and complexity that holds more significance over remaining categories. Random forest is best classifier for tracking changes with 0.99 true positive rate and 0.01 false positive rate. It improves traceability by increasing the Kappa statistic and true positive rate as compared to Understand tool.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"54 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88801696","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}
Code refactoring is the modification of structure with out altering its functionality. The refactoring task is critical for enhancing the qualities for non-functional attributes, such as efficiency, understandability, reusability, and flexibility. Our research aims to build an optimized model for refactoring prediction at the method level with 7 ensemble techniques and verities of SMOTE techniques. This research has considered 5 open source java projects to investigate the accuracy of our anticipated model, which forecasts refactoring applicants by the use of ensemble techniques (BAG-KNN, BAG-DT, BAG-LOGR, ADABST, EXTC, RANF, GRDBST). Data imbalance issues are handled using 3 sampling techniques (SMOTE, BLSMOTE, SVSMOTE) to improve refactoring prediction efficiency and also focused all features and significant features. The mean accuracy of the classifiers like BAG- DT is 99.53% ,RANF is 99.55%, and EXTC is 99.59. The mean accuracy of the BLSMOTE is 97.21%. The performance of classifiers and sampling techniques are shown in terms of the box-plot diagram.
{"title":"An empirical study for method level refactoring prediction by ensemble technique and SMOTE to improve its efficiency","authors":"","doi":"10.4018/ijossp.287612","DOIUrl":"https://doi.org/10.4018/ijossp.287612","url":null,"abstract":"Code refactoring is the modification of structure with out altering its functionality. The refactoring task is critical for enhancing the qualities for non-functional attributes, such as efficiency, understandability, reusability, and flexibility. Our research aims to build an optimized model for refactoring prediction at the method level with 7 ensemble techniques and verities of SMOTE techniques. This research has considered 5 open source java projects to investigate the accuracy of our anticipated model, which forecasts refactoring applicants by the use of ensemble techniques (BAG-KNN, BAG-DT, BAG-LOGR, ADABST, EXTC, RANF, GRDBST). Data imbalance issues are handled using 3 sampling techniques (SMOTE, BLSMOTE, SVSMOTE) to improve refactoring prediction efficiency and also focused all features and significant features. The mean accuracy of the classifiers like BAG- DT is 99.53% ,RANF is 99.55%, and EXTC is 99.59. The mean accuracy of the BLSMOTE is 97.21%. The performance of classifiers and sampling techniques are shown in terms of the box-plot diagram.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"19 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79664737","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}
Software quality engineering applied numerous techniques for assuring the quality of software, namely testing, verification, validation, fault tolerance, and fault prediction of the software. The machine learning techniques facilitate the identification of software modules as faulty or non-faulty. In most of the research, these approaches predict the fault-prone module in the same release of the software. Although, the model is found to be more efficient and validated when training and tested data are taken from previous and subsequent releases of the software respectively. The contribution of this paper is to predict the faults in two scenarios i.e. inter and intra release prediction. The comparison of both intra and inter-release fault prediction by computing various performance matrices using machine learning methods shows that intra-release prediction is having better accuracy compared to inter-releases prediction across all the releases. Also, but both the scenarios achieve good results in comparison to existing research work.
{"title":"A Software Fault Prediction on Inter- and Intra-Release Prediction Scenarios","authors":"A. Mishra, Meenu Singla","doi":"10.4018/ijossp.287611","DOIUrl":"https://doi.org/10.4018/ijossp.287611","url":null,"abstract":"Software quality engineering applied numerous techniques for assuring the quality of software, namely testing, verification, validation, fault tolerance, and fault prediction of the software. The machine learning techniques facilitate the identification of software modules as faulty or non-faulty. In most of the research, these approaches predict the fault-prone module in the same release of the software. Although, the model is found to be more efficient and validated when training and tested data are taken from previous and subsequent releases of the software respectively. The contribution of this paper is to predict the faults in two scenarios i.e. inter and intra release prediction. The comparison of both intra and inter-release fault prediction by computing various performance matrices using machine learning methods shows that intra-release prediction is having better accuracy compared to inter-releases prediction across all the releases. Also, but both the scenarios achieve good results in comparison to existing research work.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"7 1","pages":"1-18"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74409914","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}
The analysis of dynamics in networks represents a great deal in the Social Network Analysis research area. To support students, teachers, developers, and researchers in this work, we introduce a novel R package, namely DynComm. It is designed to be a multi-language package used for community detection and analysis on dynamic networks. The package introduces interfaces to facilitate further developments and the addition of new and future developed algorithms to deal with community detection in evolving networks. This new package aims to abstract the programmatic interface of the algorithms, whether they are written in R or other languages, and expose them as functions in R.
{"title":"DynComm","authors":"","doi":"10.4018/ijossp.287614","DOIUrl":"https://doi.org/10.4018/ijossp.287614","url":null,"abstract":"The analysis of dynamics in networks represents a great deal in the Social Network Analysis research area. To support students, teachers, developers, and researchers in this work, we introduce a novel R package, namely DynComm. It is designed to be a multi-language package used for community detection and analysis on dynamic networks. The package introduces interfaces to facilitate further developments and the addition of new and future developed algorithms to deal with community detection in evolving networks. This new package aims to abstract the programmatic interface of the algorithms, whether they are written in R or other languages, and expose them as functions in R.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77619897","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}
The botnet interrupts network devices and keeps control of the connections with the command, which controls the programmer, and the programmer controls the malicious code injected in the machine for obtaining information about the machines. The attacker uses a botnet to commence dangerous attacks as DDoS, phishing, despoil of information, and spamming. The botnet establishes with a large network and several hosts belong to it. In the paper, the authors proposed the framework of botnet detection by using an Artificial Neural Network. The author research upgrading the extant system by comprising of cache memory to fast the process. Finally, for detection, the author used an analytical approach, which is known as an artificial neural network that contains three layers: the input layer, hidden layer, output layer, and all layers are connected to correlate and approximate the results. The experiment result determines that the classifier with 25 epochs gives optimal accuracy is 99.78 percent and shows the detection rate is 99.7 percent.
{"title":"Comprehensive Method of Botnet Detection Using Machine Learning","authors":"Kapil Kumar","doi":"10.4018/ijossp.287613","DOIUrl":"https://doi.org/10.4018/ijossp.287613","url":null,"abstract":"The botnet interrupts network devices and keeps control of the connections with the command, which controls the programmer, and the programmer controls the malicious code injected in the machine for obtaining information about the machines. The attacker uses a botnet to commence dangerous attacks as DDoS, phishing, despoil of information, and spamming. The botnet establishes with a large network and several hosts belong to it. In the paper, the authors proposed the framework of botnet detection by using an Artificial Neural Network. The author research upgrading the extant system by comprising of cache memory to fast the process. Finally, for detection, the author used an analytical approach, which is known as an artificial neural network that contains three layers: the input layer, hidden layer, output layer, and all layers are connected to correlate and approximate the results. The experiment result determines that the classifier with 25 epochs gives optimal accuracy is 99.78 percent and shows the detection rate is 99.7 percent.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"106 1","pages":"1-25"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87931379","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 : 2021-07-01DOI: 10.4018/ijossp.2021070102
Amandeep Kaur, Munish Saini
In the software system, the code snippets that are copied and pasted in the same software or another software result in cloning. The basic cause of cloning is either a programmer‘s constraint or language constraints. An increase in the maintenance cost of software is the major drawback of code clones. So, clone detection techniques are required to remove or refactor the code clone. Recent studies exhibit the abstract syntax tree (AST) captures the structural information of source code appropriately. Many researchers used tree-based convolution for identifying the clone, but this technique has certain drawbacks. Therefore, in this paper, the authors propose an approach that finds the semantic clone through square-based convolution by taking abstract syntax representation of source code. Experimental results show the effectiveness of the approach to the popular BigCloneBench benchmark.
{"title":"Enhancing the Software Clone Detection in BigCloneBench: A Neural Network Approach","authors":"Amandeep Kaur, Munish Saini","doi":"10.4018/ijossp.2021070102","DOIUrl":"https://doi.org/10.4018/ijossp.2021070102","url":null,"abstract":"In the software system, the code snippets that are copied and pasted in the same software or another software result in cloning. The basic cause of cloning is either a programmer‘s constraint or language constraints. An increase in the maintenance cost of software is the major drawback of code clones. So, clone detection techniques are required to remove or refactor the code clone. Recent studies exhibit the abstract syntax tree (AST) captures the structural information of source code appropriately. Many researchers used tree-based convolution for identifying the clone, but this technique has certain drawbacks. Therefore, in this paper, the authors propose an approach that finds the semantic clone through square-based convolution by taking abstract syntax representation of source code. Experimental results show the effectiveness of the approach to the popular BigCloneBench benchmark.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"71 1","pages":"17-31"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88109657","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：