Table 4.

Performance comparisons for malware classification and detection using both datasets with 229 × 229.

Dataset 1 (229 × 229)
	Methods	Precision (%)	Recall (%)	F1-Score (%)	Accuracy (%)
Classification	GNB	86	90	86	87.21
	SVM	95	89	81	93.11
	DT	98	98	97	98.03
	LR	95	89	91	93.34
	RF	98	97	98	98.03
	Ensemble	98	97	98	98.18
Detection	GNB	94	91	92	92.24
	SVM	93	93	92	92.16
	DT	99	99	98	98.94
	LR	93	93	92	92.16
	RF	99	99	99	99.02
	Ensemble	99	99	99	99.02
Dataset 2 (229 × 229)
Classification	GNB	98	95	96	98.02
	SVM	96	92	94	95.96
	DT	95	95	94	95.04
	LR	98	97	97	97.98
	RF	97	97	97	97.02
	Ensemble	98	98	98	98.1
Detection	GNB	94	93	93	93.11
	SVM	93	91	91	91.08
	DT	99	99	99	98.96
	LR	95	93	93	93.1
	RF	99	99	99	99.04
	Ensemble	95	93	93	94.16