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

Table 13

The selected best model in terms of cross-validation score.

	k = 1	k = 2	k = 3	k = 4	k = 5	k = 6	k = 7	k = 8	k = 9	k = 10	Average
(a) Static features
TPOT, without feature selection
F-measure	0.92	0.82	0.82	0.97	0.93	0.86	0.97	0.92	1.00	0.93	0.91
Precision	1.00	0.75	0.75	1.00	0.90	1.00	1.00	0.95	1.00	0.90	0.93
Recall	0.85	0.90	0.90	0.95	0.95	0.75	0.95	0.90	1.00	0.95	0.91
Random forest, with feature selection
F-measure	0.92	0.74	0.86	0.93	0.85	0.83	0.97	0.93	0.97	0.84	0.89
Precision	0.95	0.65	0.79	0.90	0.84	0.93	1.00	0.90	0.95	0.89	0.88
Recall	0.90	0.85	0.95	0.95	0.85	0.75	0.95	0.95	0.95	0.80	0.89
(b) Dynamic features
TPOT, without feature selection
F-measure	0.90	0.90	0.97	0.85	0.79	0.97	1.00	1.00	1.00	1.00	0.94
Precision	1.00	0.93	1.00	0.91	1.00	1.00	1.00	1.00	1.00	1.00	0.98
Recall	0.87	0.93	0.73	0.67	0.80	1.00	1.00	1.00	1.00	1.00	0.90
TPOT, with feature selection
F-measure	0.89	0.90	0.93	0.67	0.84	0.93	0.97	1.00	1.00	1.00	0.91
Precision	1.00	0.93	1.00	0.75	0.81	0.93	1.00	1.00	1.00	1.00	0.94
Recall	0.80	0.87	0.87	0.60	0.87	0.93	0.93	1.00	1.00	1.00	0.89
(c) Hybrid features
Native Bayes, with feature selection
F-measure	0.93	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	0.99
Precision	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00
Recall	0.88	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	0.99
TPOT, with feature selection
F-measure	0.93	1.00	1.00	0.92	0.92	0.92	1.00	1.00	1.00	1.00	0.97
Precision	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00	1.00
Recall	0.88	1.00	1.00	0.86	0.86	0.86	1.00	1.00	1.00	1.00	0.94