Research Article

Cross-Project Defect Prediction Based on Two-Phase Feature Importance Amplification

Table 1

Details of AEEEM database.

ProjectsTypes of projectsModulesDefective modulesDefective ratio (%)

EQOSGI framework32512939.692
JDTDevelopment99720620.662
LCText search engine library3996416.040
MLTask management186224513.158
PDEDevelopment149220914.008