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

Table 4

Comparative results for the PC1 dataset.

PC1
Algorithm	Precision	Recall	F-measure	Accuracy
RF	0.950	0.984	0.960	93.680
DT	0.937	0.990	0.960	92.870
NB	0.947	0.936	0.942	89.170
Without dropout DNN	0.940	0.990	0.970	93.000
With dropout DNN	0.930	1.000	0.960	96.000