Kernel CCA Based Transfer Learning for Software Defect Prediction

Ying MA  Shunzhi ZHU  Yumin CHEN  Jingjing LI  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E100-D    No.8    pp.1903-1906
Publication Date: 2017/08/01
Publicized: 2017/04/28
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2016EDL8238
Type of Manuscript: LETTER
Category: Software Engineering
Keyword: 
machine learning,  defect prediction,  transfer learning,  kernel canonical correlation analysis,  

Full Text: PDF(188KB)>>
Buy this Article



Summary: 
An transfer learning method, called Kernel Canonical Correlation Analysis plus (KCCA+), is proposed for heterogeneous Cross-company defect prediction. Combining the kernel method and transfer learning techniques, this method improves the performance of the predictor with more adaptive ability in nonlinearly separable scenarios. Experiments validate its effectiveness.


open access publishing via