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

Table 2

Comparative results for the KC1 dataset.

KC1
Algorithm	Precision	Recall	F-measure	Accuracy
RF	0.887	0.965	0.925	86.670
DT	0.865	0.974	0.916	84.870
NB	0.888	0.905	0.897	82.360
Without dropout DNN	0.790	0.970	0.940	88.570
With dropout DNN	0.850	1.000	0.920	92.000