Table 3.

Results of the classification performed by the RF, the proposed deep learning model, and the ensemble learning method.

Model	Features	Accuracy	Precision	Recall	Specificity	AUC-ROC
RF	10	0.69 ± 0.10	0.70 ± 0.15	0.70 ± 0.17	0.69 ± 0.14	0.70 ± 0.10
RF	18	0.70 ± 0.11	0.71 ± 0.14	0.70 ± 0.17	0.71 ± 0.15	0.70 ± 0.11
RF	33	0.73 ± 0.13	0.73 ± 0.15	0.70 ± 0.17	0.76 ± 0.13	0.73 ± 0.13
Proposed		0.78 ± 0.08	0.82 ± 0.13	0.77 ± 0.15	0.79 ± 0.17	0.78 ± 0.08
Ensemble		0.80 ± 0.08	0.82 ± 0.14	0.82 ± 0.14	0.78 ± 0.18	0.80 ± 0.08