A Paired Learner-Based Approach for Concept Drift Detection and Adaptation in Software Defect Prediction

dc.authorid Kumar, Dr Sandeep/0000-0003-0747-6776
dc.authorid Kumar, Sandeep/0000-0002-3250-4866
dc.authorid Mishra, Alok/0000-0003-1275-2050
dc.authorid Kumar, Sandeep/0000-0001-9633-407X
dc.authorscopusid 57226450033
dc.authorscopusid 57218539729
dc.authorscopusid 7201441575
dc.authorwosid Kumar, Dr Sandeep/AAW-6313-2020
dc.authorwosid Gangwar, Arvind Kumar Kumar/JHT-1207-2023
dc.authorwosid Kumar, Sandeep/AAW-6570-2020
dc.authorwosid Mishra, Alok/AAE-2673-2019
dc.contributor.author Gangwar, Arvind Kumar
dc.contributor.author Kumar, Sandeep
dc.contributor.author Mishra, Alok
dc.contributor.other Software Engineering
dc.date.accessioned 2024-07-05T15:19:37Z
dc.date.available 2024-07-05T15:19:37Z
dc.date.issued 2021
dc.department Atılım University en_US
dc.department-temp [Gangwar, Arvind Kumar; Kumar, Sandeep] Indian Inst Technol Roorkee, Dept Comp Sci & Engn, Roorkee 247667, Uttar Pradesh, India; [Mishra, Alok] Molde Univ Coll Specialized Univ Logist, Fac Logist, N-6410 Molde, Norway; [Mishra, Alok] Atilim Univ, Dept Software Engn, TR-06830 Ankara, Turkey en_US
dc.description Kumar, Dr Sandeep/0000-0003-0747-6776; Kumar, Sandeep/0000-0002-3250-4866; Mishra, Alok/0000-0003-1275-2050; Kumar, Sandeep/0000-0001-9633-407X en_US
dc.description.abstract The early and accurate prediction of defects helps in testing software and therefore leads to an overall higher-quality product. Due to drift in software defect data, prediction model performances may degrade over time. Very few earlier works have investigated the significance of concept drift (CD) in software-defect prediction (SDP). Their results have shown that CD is present in software defect data and tha it has a significant impact on the performance of defect prediction. Motivated from this observation, this paper presents a paired learner-based drift detection and adaptation approach in SDP that dynamically adapts the varying concepts by updating one of the learners in pair. For a given defect dataset, a subset of data modules is analyzed at a time by both learners based on their learning experience from the past. A difference in accuracies of the two is used to detect drift in the data. We perform an evaluation of the presented study using defect datasets collected from the SEACraft and PROMISE data repositories. The experimentation results show that the presented approach successfully detects the concept drift points and performs better compared to existing methods, as is evident from the comparative analysis performed using various performance parameters such as number of drift points, ROC-AUC score, accuracy, and statistical analysis using Wilcoxon signed rank test. en_US
dc.identifier.citationcount 3
dc.identifier.doi 10.3390/app11146663
dc.identifier.issn 2076-3417
dc.identifier.issue 14 en_US
dc.identifier.scopus 2-s2.0-85111559250
dc.identifier.uri https://doi.org/10.3390/app11146663
dc.identifier.uri https://hdl.handle.net/20.500.14411/1996
dc.identifier.volume 11 en_US
dc.identifier.wos WOS:000675935700001
dc.identifier.wosquality Q2
dc.institutionauthor Mıshra, Alok
dc.language.iso en en_US
dc.publisher Mdpi en_US
dc.relation.publicationcategory Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/openAccess en_US
dc.scopus.citedbyCount 3
dc.subject concept drift en_US
dc.subject naive Bayes en_US
dc.subject random forest en_US
dc.subject software defect prediction en_US
dc.subject software quality assurance en_US
dc.title A Paired Learner-Based Approach for Concept Drift Detection and Adaptation in Software Defect Prediction en_US
dc.type Article en_US
dc.wos.citedbyCount 3
dspace.entity.type Publication
relation.isAuthorOfPublication de97bc0b-032d-4567-835e-6cd0cb17b98b
relation.isAuthorOfPublication.latestForDiscovery de97bc0b-032d-4567-835e-6cd0cb17b98b
relation.isOrgUnitOfPublication d86bbe4b-0f69-4303-a6de-c7ec0c515da5
relation.isOrgUnitOfPublication.latestForDiscovery d86bbe4b-0f69-4303-a6de-c7ec0c515da5

Files

Collections