.png){kind=icon}
.png){kind=icon}
Return
SGEOM: Sample gradient entropy based oversampling method for the class-imbalanced problem in software defect prediction
.png){kind=icon}
PRE
AI
DOI：10.1016/j.asoc.2026.115225.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We introduce a novel metric termed Sample Gradient Entropy (SGE). • We use SGE as a criterion for selecting nearest neighbors for KNN. • We present a novel method for synthesizing defective samples.
Keywords:
Sample Gradient Entropy
KNN
Oversampling
Software Defect Prediction
Class-Imbalanced Problem
Journal
IF:
6.6
Papers:
1.4W
Citations:
4.8W