. 2022 Feb 24;22(5):1793. doi: 10.3390/s22051793

Table 3.

Performance metrics for the best-performing combinations (feature selection technique and number of features) for the 10 ML Classifiers.

Classifier	Feature Selection	# of Feature	95% Confidence Interval Results					Inference Time (ms)
Classifier	Feature Selection	# of Feature	Accuracy	Precision	Sensitivity	F1-Score	Specificity	Inference Time (ms)
MLP	XGBoost	2	0.91 ± 01.19	0.91 ± 01.19	0.91 ± 01.19	0.91 ± 01.19	0.91 ± 01.19	0.592
Extra Tree	Random Forest	5	0.88 ± 01.17	0.88 ± 01.17	0.88 ± 01.17	0.88 ± 01.17	0.88 ± 01.17	0.406
Random Forest	XGBoost	2	0.87 ± 01.17	0.87 ± 01.17	0.87 ± 01.17	0.87 ± 01.17	0.87 ± 01.17	0.412
KNN	XGBoost	2	0.87 ± 01.17	0.87 ± 01.17	0.87 ± 01.17	0.87 ± 01.17	0.87 ± 01.17	0.464
SVM	XGBoost	2	0.86 ± 01.16	0.86 ± 01.16	0.86 ± 01.16	0.86 ± 01.16	0.86 ± 01.16	0.456
Gradient Boost	XGBoost	2	0.84 ± 01.15	0.84 ± 01.15	0.84 ± 01.15	0.85 ± 01.15	0.84 ± 01.15	0.492
XGBoost	Random Forest	5	0.84 ± 01.15	0.84 ± 01.15	0.84 ± 01.15	0.84 ± 01.15	0.84 ± 01.15	0.426
Logistic Regression	Random Forest	2	0.81 ± 01.13	0.81 ± 01.13	0.81 ± 01.13	0.81 ± 01.13	0.81 ± 01.13	0.532
LDA	Random Forest	9	0.78 ± 01.11	0.78 ± 01.11	0.78 ± 01.11	0.78 ± 01.11	0.78 ± 01.11	0.406
AdaBoost	Random Forest	3	0.68 ± 01.03	0.68 ± 01.03	0.68 ± 01.03	0.70 ± 01.05	0.68 ± 01.03	0.492