Impact of Parameter Tuning for Optimizing Deep Neural Network Models for Predicting Software Faults

Table 7

Confusion matrix analysis for the KC1, KC3, PC1, and PC2 datasets (TPR: True Positive Rate, TNR: True Negative Rate, FPR: False Positive Rate, and FNR: False Negative Rate).

Algorithm	KC1				KC3				PC1				PC2
	TPR	TNR	FPR	FNR	TPR	TNR	FPR	FNR	TPR	TNR	FPR	FNR	TPR	TNR	FPR	FNR
RF	0.330	0.960	0.040	0.670	0.140	0.970	0.030	0.860	0.290	0.980	0.015	0.700	0.000	1.000	0.000	1.000
DT	0.170	0.970	0.030	0.830	0.380	0.910	0.070	0.610	0.290	0.930	0.060	0.700	0.130	0.920	0.070	0.880
NB	0.380	0.900	0.070	0.620	0.380	0.900	0.120	0.610	0.290	0.930	0.060	0.700	0.130	0.920	0.070	0.880
Without dropout DNN	0.470	0.980	0.020	0.530	0.170	0.970	0.030	0.830	0.020	0.990	0.010	0.980	0.020	0.990	0.010	0.980
With dropout DNN	0.520	0.980	0.017	0.470	0.970	0.980	0.012	0.026	0.410	0.980	0.011	0.580	1.000	0.990	0.001	0.000