Software Defect Prediction through Neural Network and Feature Selections

Table 6

Comparison of RBF results with other previous methods before feature selection for CM1 data set.

Source	Algorithm	F-measure	Accuracy
[31]	RF	0.83	83.00%
	DS	0.79	78.00%
	SVM	0.78	75.00%
[47]	Naive Bayes	0.91	83.45%
	MLP	0.94	89.55%
	SVM	0.95	91.97%
	RBF	0.95	90.33%
[42]	J48	N/A	88.60%
This research	RBF	0.96	93.99