. 2021 Sep 16;150(3):1945–1953. doi: 10.1121/10.0006104

TABLE III.

Results of accuracy, precision, recall, and F1-score for different ML models based on the total number of true positive (TP), true negative (TN), false positive (FP), and false negative (FN).

Models	Accuracy^a	Precision^b	Recall^c	F1-score^d
SVM	87.43	86.55	88.18	86.61
LR	89.43	90.17	90.39	90.28
DT	83.02	82.67	86.94	84.75
KNN	85.29	8364	90.64	87.00
FFNN	89.71	89.63	91.63	90.62
GNB	83.29	82.16	88.42	85.18

^{^a}

$Accuracy = (T P + T N) / (T P + T N + F P + F N) .$

^{^b}

$Precision=TP/ (T P + F P) .$

^{^c}

$Recall=TP/ (T P + F N) .$

^{^d}

$F1 - score = [2 \times (precision \times r ecall)] / (precision + r ecall) .$