An Attribute Extraction for Automated Malware Attack Classification and Detection Using Soft Computing Techniques

Table 6

Various attitudes for selecting features in relation to classification techniques for 100% training.

Attribute extraction	No. of attributes	ANN (Acc, TPR, FPR, TNR, FNR) (%)	Decision tree (Acc, TPR, FPR, TNR, FNR) (%)	Naive Bayes (Acc, TPR, FPR, TNR, FNR) (%)	SVM (Acc, TPR,FPR, TNR, FNR) (%)
CFsSubset	25	89.9	91.3	87.9	93.3
		100	100	100	100
		11.9	13	15	10
		86.8	88	88.9	90
		0	0	0	0
PCA	55	87.9	93.5	88.9	94.8
		63.8	77	74	96
		5	4	11	6
		94.8	97	91	98
		34.7	22	25	0
GainRatioAttribute	201	90.5	93.8	86.7	94.5
		1	100	100	100
		9	10	17	8
		90	89	86	91
		0	0	0	0
SymmetricalUncertAttributeEval	146	93.5	93.8	89.3	95.5
		100	100	100	100
		9.9	10	11	8
		88.7	89.6	83	91
		0	0	0	0