. 2021 May 18;106(2):1453–1475. doi: 10.1007/s11071-021-06504-1

Table 6.

Experimental results of studied feature selection algorithms for dataset 2

Feature selection $+$ classifier	Accuracy (%)	Precision (%)	Sensitivity (%)	Specificity (%)	F1-score (%)	AUC (%)
$SFS + MLP$	92.62	92.62	92.62	93.90	92.62	93.26
$SFS + SVM$	92.88	92.88	92.88	94.91	92.88	93.89
$SFS + LR$	93.75	93.75	93.75	94.90	93.75	94.32
$SFS + DT$	86.47	86.47	86.47	87.24	86.47	86.86
$SFS + GB$	92.51	92.51	92.51	93.92	92.51	93.22
$SFS + RF$	92.62	92.62	92.62	93.90	92.62	93.26
$SFS + XGBoost$	92.51	92.51	92.51	93.94	92.51	93.23
$SFS + AdaBoost$	92.52	92.52	92.52	93.91	92.52	93.22
$SFFS + MLP$	92.62	92.62	92.62	93.90	92.62	93.26
$SFFS + SVM$	94.01	94.01	94.01	99.60	94.01	96.81
$SFFS + LR$	95.31	95.31	95.31	98.2	95.31	96.75
$SFFS + DT$	92.61	92.61	92.61	93.90	92.61	93.26
$SFFS + GB$	92.62	92.62	92.62	93.90	92.62	93.26
$SFFS + RF$	91.68	91.68	91.68	92.77	91.68	92.23
$SFFS + XGBoost$	95.10	95.10	95.10	98.25	95.10	96.67
$SFFS + AdaBoost$	95.34	95.34	95.34	98.23	95.34	96.79
$SBS + MLP$	91.68	91.68	91.68	92.77	91.68	92.23
$SBS + SVM$	92.88	92.88	92.88	94.91	92.88	93.89
$SBS + LR$	95.12	95.12	95.12	98.20	95.12	96.66
$SBS + DT$	86.47	86.47	86.47	87.24	86.47	86.86
$SBS + GB$	92.51	92.51	92.51	93.92	92.51	93.22
$SBS + RF$	92.62	92.62	92.62	93.90	92.62	93.26
$SBS + XGBoost$	95.34	95.34	95.34	98.23	95.34	96.79
$SBS + AdaBoost$	91.68	91.68	91.68	92.77	91.68	92.23
$NSGA-II + MLP$	91.64	91.64	91.64	95.26	91.64	93.45
$NSGA-II + SVM$	95.10	95.10	95.10	98.25	95.10	96.67
$NSGA-II + LR$	94.76	94.76	94.76	98.24	94.76	96.50
$NSGA-II + DT$	92.52	92.52	92.52	93.91	92.52	93.22
$NSGA-II + GB$	95.34	95.34	95.34	98.23	95.34	96.79
$NSGA-II + RF$	92.44	92.44	92.44	93.91	92.44	93.17
$NSGA-II + XGBoost$	92.62	92.62	92.62	93.90	92.62	93.26
$NSGA - I I + AdaBoost$	95.56	95.56	95.56	98.19	95.56	96.87

Bold value indicates the highest result