Cross-Project Defect Prediction Using Transfer Learning with Long Short-Term Memory Networks

Table 6

f-measure of different models on the NASA dataset.

Target project	LR	NNFilter	TCA	DBN	DPDBN	DPCNN	DPTCNN	TLSTM	DPTLSTM
CM1	0.288	0.29	0.229	0.261	0.287	0.325	0.36	0.369	0.37
JM1	0.403	0.365	0.351	0.446	0.461	0.528	0.533	0.591	0.627
KC1	0.608	0.606	0.609	0.626	0.64	0.651	0.68	0.677	0.687
KC3	0.604	0.513	0.732	0.733	0.769	0.778	0.786	0.811	0.8
MW1	0.379	0.599	0.377	0.423	0.433	0.457	0.485	0.575	0.585
PC2	0.603	0.61	0.611	0.566	0.58	0.605	0.611	0.713	0.805

The values in bold represent the most optimal values in a row of data.