Table 1.

Four-class classification performances of NB, LDA, and SVM algorithms when trained with fNIRS only features (i.e., GE_cm and GE_dm). Each performance metric is represented in percentages (%) as the mean value across all runs ± standard deviation of the mean.

Method	Accuracy	Precision	Recall	Specificity	F1-Score
NB	81.77 ± 1.06	82.1 ± 1	81 ± 0.01	94 ± 0.004	81 ± 1
LDA	83.8 ± 1	85 ± 0.01	83 ± 0.01	95 ± 0.01	84 ± 0.01
SVM	81 ± 0.84	80 ± 0.01	79 ± 0.01	94 ± 0.003	80 ± 0.008