Software Defect Prediction through Neural Network and Feature Selections

Table 19

Comparison of RBF results with other previous methods before feature selection for PC5 data set.

Source	Algorithm	F-measure	Accuracy
[47]	Naive Bayes	0.98	96.03%
	MLP	0.99	97.03%
	SVM	0.99	97.23%
	RBF	0.99	87.27%
[31]	RF	0.76	76.00%
	DS	0.72	71.01%
	SVM	0.69	68.01%
	LR	0.70	68.00%
[49]	RBF	0.23	75.79%
	KNN	0.49	73.03%
	DT	0.53	75.00%
This research	RBF	0.80	79.02