Software Defect Prediction through Neural Network and Feature Selections

Table 9

Comparison of RBF results with other previous methods before feature selection for KC2 data set.

Source	Algorithm	F-measure	Accuracy
[3]	MLP	N/A	79.64%
[47]	Naive Bayes	0.90	84.78%
	MLP	0.90	83.64%
	SVM	0.90	82.34%
	RBF	0.90	83.63%
[42]	J48	N/A	81.36%
[31]	RF	0.82	82.00%
	DS	0.78	78.01%
	SVM	0.80	79.10%
This research	RBF	0.82	79.11