Table 9 Results of the predicting models.

Classifier	Feature selection method	Number of selected features	Accuracy (%)	Sensitivity (%)	Specificity (%)	Positive predictive value (%)	Negative predictive value (%)
Random	AOA	100	97.35	95.90	98.66	98.47	96.39
Forest	SCA	113	97.00	96.27	97.65	97.36	96.68
	WOA	113	96.29	95.52	96.98	96.60	96.01
	GNDO	110	97.53	97.01	97.99	97.74	97.33
	GWO	103	97.35	96.27	98.32	98.10	96.70
	IGWO	92	98.06	96.64	99.33	99.23	97.05
	PSO	114	96.82	95.90	97.65	97.35	96.36
	h-PSOGNDO	81	98.76	98.88	98.66	98.51	98.99
Support	AOA	100	92.76	95.15	90.60	90.11	95.41
Vector	SCA	113	94.52	94.78	94.30	93.73	95.25
Machine	WOA	113	93.99	94.78	93.29	92.70	95.21
	GNDO	110	93.82	95.52	92.28	91.76	95.82
	GWO	103	93.11	92.91	93.29	92.57	93.60
	IGWO	92	93.82	95.90	91.95	91.46	96.14
	PSO	114	94.17	94.78	93.62	93.04	95.22
	h-PSOGNDO	81	94.70	96.64	92.95	92.50	96.85
Naïve	AOA	100	80.74	77.24	83.89	81.18	80.39
Bayes	SCA	113	82.86	83.96	81.88	80.65	85.02
	WOA	113	83.39	81.34	85.23	83.21	85.23
	GNDO	110	81.63	77.24	85.57	82.80	80.70
	GWO	103	83.39	81.72	84.90	82.95	83.77
	IGWO	92	83.92	79.10	88.26	85.83	82.45
	PSO	114	79.68	76.12	82.89	80.00	79.42
	h-PSOGNDO	81	87.63	86.19	88.93	87.50	87.75
KNN	AOA	100	96.9	96.41	97.50	97.50	96.53
	SCA	113	97.50	98.50	95.52	96.34	98.5
	WOA	113	96.94	97.39	98.50	98.50	97.51
	GNDO	110	96.33	98.13	94.53	94.26	98.15
	GWO	103	97.61	97.39	97.84	97.76	97.51
	IGWO	92	96.99	98.13	95.86	95.63	98.16
	PSO	114	96.86	95.55	98.16	98.12	95.91
	h-PSOGNDO	81	98.32	98.16	98.50	98.50	98.13

Quick links

Search