Table 5.

Performance evaluation of different ML models using fscnca feature selection technique for NCS.

	Features	Accuracy (%)	Sensitivity (%)	Specificity (%)	F1-score (%)	Error rate	MCC	Kappa	AUC
RF	Top 10	93.26 ± 0.91	91.95 ± 1.03	98.95 ± 0.62	91.80 ± 1.07	0.07 ± 0.01	0.90	0.82	1.00
EC	Top 10	93.16 ± 0.89	91.49 ± 1.00	98.38 ± 0.78	91.62 ± 0.96	0.07 ± 0.01	0.89	0.82	1.00
DT	Top 10	91.60 ± 1.95	90.19 ± 2.36	99.40 ± 0.47	89.78 ± 2.44	0.08 ± 0.02	0.87	0.78	0.98
KNN	Top 10	79.47 ± 0.94	75.71 ± 0.89	91.95 ± 1.05	75.89 ± 1.01	0.21 ± 0.01	0.69	0.45	0.91
SVM	Top 8	75.03 ± 1.42	68.17 ± 1.76	72.69 ± 2.70	71.95 ± 1.65	0.25 ± 0.01	0.63	0.33	0.95
NB	Top 10	73.90 ± 2.02	72.35 ± 2.16	95.31 ± 1.01	72.43 ± 2.02	0.26 ± 0.02	0.64	0.30	0.95
LR	Top 10	71.57 ± 1.92	69.15 ± 1.88	93.33 ± 1.27	68.91 ± 1.84	0.28 ± 0.02	0.59	0.24	0.95
DAC	Top 10	70.33 ± 2.09	68.15 ± 2.04	93.96 ± 1.42	68.05 ± 1.95	0.30 ± 0.02	0.58	0.21	0.93