Software Defect Prediction through Neural Network and Feature Selections

Table 17

Comparison of RBF results with other previous methods before feature selection for PC3 data set.

Source	Algorithm	F-measure	Accuracy
[47]	Naive Bayes	0.60	46.87%
	MLP	0.94	87.55
	SVM	0.95	89.33%
	RBF	0.95	89.76%
[31]	RF	0.84	84.00%
	DS	0.81	80.00%
	SVM	0.78	74.00%
	LR	0.79	84.00%
[49]	RBF	N/A	86.39%
	KNN	0.35	86.07%
	DT	0.35	86.39%
This research	RBF	0.97	94.11%