cHybriDroid: A Machine Learning-Based Hybrid Technique for Securing the Edge Computing

Table 12

The summary of results with and without feature selection.

	(a) Static features results			(b) Dynamic features results			(c) Hybrid feature results
	F-meas.	Prec.	Recall	F-meas.	Prec.	Recall	F-meas.	Prec.	Recall
WO Feat. Sel.
SVM	0.90	0.90	0.91	0.90	0.90	0.92	0.93	1.00	0.89
Decision tree	0.83	0.84	0.84	0.84	0.85	0.84	0.88	0.96	0.83
Random forest	0.89	0.85	0.83	0.89	0.86	0.84	0.96	0.98	0.93
K-star	0.84	0.91	0.8	0.85	0.92	0.80	0.57	1.00	0.42
Naive Bayes	0.85	0.98	0.75	0.85	0.99	0.75	0.99	1.00	0.99
TPOT	0.91	0.92	0.91	0.94	0.98	0.90	0.99	1.00	0.99
With feat. sel.
SVM	0.86	0.86	0.88	0.90	0.94	0.87	0.95	1.00	0.91
Decision tree	0.87	0.86	0.89	0.91	0.95	0.87	0.91	0.97	0.87
Random forest	0.88	0.88	0.89	0.90	0.94	0.87	0.95	0.96	0.95
K-star	0.84	0.77	0.94	0.83	0.83	0.87	0.84	1.00	0.74
Naive Bayes	0.79	0.68	0.94	0.83	0.97	0.73	0.96	1.00	0.93
TPOT	0.87	0.87	0.88	0.91	0.94	0.89	0.97	1.00	0.94