Naslov
Software defect prediction using semi-supervised learning with dimension reduction

Autori
Lu, Huihua ; Čukić, Bojan ; Culp, Mark

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proc. of IEEE/ACM International Conference on Automated Software Engineering, ASE 2012 / Goedicke, Michael ; Menzies, Tim ; Saeki, Motoshi - New York (NY) : The Association for Computing Machinery (ACM), 2012, 314-317

ISBN
978-1-4503-1204-2

Skup
IEEE/ACM International Conference on Automated Software Engineering, ASE 2012

Mjesto i datum
Essen, Njemačka, 03.09.2012. - 07.09.2012

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
software fault prediction; semi-supervised learning; dimension reduction; software metrics

Sažetak
Accurate detection of fault prone modules offers the path to high quality software products while minimizing non essential assurance expenditures. This type of quality modeling requires the availability of software modules with known fault content developed in similar environment. Establishing whether a module contains a fault or not can be expensive. The basic idea behind semi-supervised learning is to learn from a small number of software modules with known fault content and supplement model training with modules for which the fault information is not available. In this study, we investigate the performance of semi-supervised learning for software fault prediction. A preprocessing strategy, multidimensional scaling, is embedded in the approach to reduce the dimensional complexity of software metrics. Our results show that the semi-supervised learning algorithm with dimension-reduction preforms significantly better than one of the best performing supervised learning algorithms, random forest, in situations when few modules with known fault content are available for training.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA