Skip to main content

Table 2 Performance of transformer model for EEG signals with eyes open on different methods for five class (ADHD, MDD, OCD, SMC, and Healthy) classification

From: Transformers for autonomous recognition of psychiatric dysfunction via raw and imbalanced EEG signals

Decision

Method

Accuracy

F1-score

Precision

Recall

Window-level

Trans + CCE

63.21

41.99

42.51

41.49

Trans + Focal Loss (\(\gamma = 2)\)

61.25

40.91

41.65

40.20

Trans + Focal Loss (\(\gamma = 0.5)\)

60.27

37.59

36.38

41.27

Trans + WCCE

53.30

43.67

44.64

42.73

Patient-level

Trans + CCE

64.38

42.90

42.81

43.96

Trans + Focal Loss (\(\gamma = 2)\)

68.49

43.29

45.00

41.72

Trans + Focal Loss (\(\gamma = 0.5)\)

61.64

38.78

39.66

40.90

Trans + WCCE

57.53

45.03

45.33

44.75

  1. The best performance is in bold