Table 4.

Comparisons of the average accuracies and standard deviations (%) of EEG-based SAD severity classification by using PDC values.

Features	Classifiers	Evaluation metrics	Delta	Theta	Alpha	Beta
PDC features	KNN	Sensitivity	93.52 ± 0.61	98.31 ± 0.52	98.85 ± 0.83	91.32 ± 2.23
		Specificity	92.82 ± 1.77	95.91 ± 4.01	94.32 ± 0.79	87.82 ± 0.79
		Accuracy	75.00 ± 4.40	70.83 ± 2.67	76.54 ± 2.76	74.37 ± 3.58
	LDA	Sensitivity	94.83 ± 1.75	95.66 ± 1.044	99.32 ± 1.38	96.83 ± 0.75
		Specificity	93.00 ± 4.44	93.62 ± 3.56	97.87 ± 3.46	94.61 ± 2.49
		Accuracy	67.00 ± 7.71	62.83 ± 7.26	68.08 ± 6.59	66.58 ± 7.39
	NB	Sensitivity	97.18 ± 1.87	97.12 ± 1.0	85.71 ± 16.07	92.15 ± 2.32
		Specificity	96.28 ± 2.17	96.33 ± 3.01	85.18 ± 1.51	94.23 ± 0.77
		Accuracy	79.70 ± 2.52	71.47 ± 2.07	79.75 ± 1.91	87.10 ± 2.11
	DT	Sensitivity	92.71 ± 7.10	89.30 ± 9.23	93.91 ± 11.12	91.80 ± 0.86
		Specificity	91.28 ± 6.20	81.84 ± 8.09	91.14 ± 4.51	92.82 ± 5.31
		Accuracy	75.95 ± 4.15	72.12 ± 3.68	75.62 ± 2.24	75.00 ± 2.74
	SVM	Sensitivity	91.27 ± 6.20	94.27 ± 6.13	93.25 ± 4.27	91.53 ± 6.47
		Specificity	90.13 ± 6.81	93.23 ± 6.81	92.12 ± 5.91	90.19 ± 9.28
		Accuracy	79.29 ± 5.93	83.66 ± 6.72	82.79 ± 7.86	80.08 ± 10.94