Software defect prediction using stacked denoising autoencoders and two-stage ensemble learning

Article ID	Journal	Published Year	Pages	File Type
6948096	Information and Software Technology	2018	29 Pages	PDF

Abstract

It can be concluded that (1) deep representations are promising for SDP compared with traditional software metrics, (2) TSE is more effective for addressing the class-imbalance problem in SDP compared with classic ensemble learning methods, and (3) the proposed SDAEsTSE is significantly effective for SDP.

Keywords

Software Metrics Software defect prediction Deep learning Ensemble learning

Related Topics

Physical Sciences and Engineering Computer Science Human-Computer Interaction

Preview

Software defect prediction using stacked denoising autoencoders and two-stage ensemble learning

Authors

Haonan Tong, Bin Liu, Shihai Wang,