Table 3.

Comparison of the classification effects of various methods.

Model	Dataset	PRE	SEN	SPE	ACC	F1	ROC-AUC	PR-AUC
USEE3	Training	0.8594	0.9649	0.9546	0.9569	0.9091	0.9908	0.9480
	Testing	0.7619	0.8421	0.9242	0.9059	0.8000	0.9553	0.8327
RF	Training	1.0000	0.9649	1.0000	0.9922	0.9821	0.9825	0.9864
	Testing	0.8000	0.6316	0.9546	0.8824	0.7059	0.7931	0.7507
AdaBoost	Training	–	0	1	0.7765	–	0.3912	–
	Testing	–	0	1	0.7765	–	0.3788	–
RUSBoost	Training	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000	1.0000
	Testing	0.8000	0.6316	0.9546	0.8824	0.7059	0.9139	0.8201