DSpace Repository

An Ensemble Approach of Simple Regression Models to Cross-Project Fault Prediction

Show simple item record

dc.contributor.author Uchigaki, Satoshi
dc.contributor.author Uchida, Shinji
dc.contributor.author Toda, Koji
dc.contributor.author Monden, Akito
dc.date.accessioned 2018-10-30T04:57:15Z
dc.date.available 2018-10-30T04:57:15Z
dc.date.issued 2012
dc.identifier.isbn 9781467321204
dc.identifier.uri http://hdl.handle.net/10061/12750
dc.description 2012 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, 8-10 Aug. 2012, Kyoto, Japan
dc.description.abstract In software development, prediction of fault-prone modules is an important challenge for effective software testing. However, high prediction accuracy may not be achieved in cross-project prediction, since there is a large difference in distribution of predictor variables between the base project (for building prediction model) and the target project (for applying prediction model.) In this paper we propose an prediction technique called an ensemble of simple regression models to improve the prediction accuracy of cross-project prediction. The proposed method uses weighted sum of outputs of simple (e.g. 1-predictor variable) logistic regression models to improve the generalization ability of logistic models. To evaluate the performance of the proposed method, we conducted 132 combinations of cross-project prediction using datasets of 12 projects from NASA IV&V Facility Metrics Data Program. As a result, the proposed method outperformed conventional logistic regression models in terms of AUC of the Alberg diagram.
dc.language.iso en
dc.publisher IEEE
dc.rights c Copyright IEEE 2012
dc.subject aerospace computing
dc.subject fault diagnosis
dc.subject program testing
dc.subject project management
dc.subject regression analysis
dc.subject simple regression model ensemble approach
dc.subject cross-project fault prediction
dc.subject software development
dc.subject fault-prone module prediction
dc.subject software testing
dc.subject predictor variable distribution
dc.subject base project
dc.subject target project
dc.subject logistic regression models
dc.subject logistic model generalization ability
dc.subject NASA IV&V Facility Metrics Data Program
dc.subject AUC
dc.subject Alberg diagram
dc.subject Software engineering
dc.subject Artificial intelligence
dc.subject Distributed computing
dc.subject fault-prone module prediction
dc.subject product metrics
dc.subject empirical study
dc.title An Ensemble Approach of Simple Regression Models to Cross-Project Fault Prediction
dc.type.nii Conference Paper
dc.identifier.fulltexturl https://doi.org/10.1109/SNPD.2012.34
dc.textversion author
dc.identifier.spage 476
dc.identifier.epage 480
dc.relation.doi 10.1109/SNPD.2012.34


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account