Skip to main content

Table 2 Dataset 1 short window (\(w=0.5\,\text{s}\)) features grand average (across all participants) accuracy and F1 score of sLDA classification, shown by condition, types of features and types of TFRs calculated with Rényi entropy

From: Detection of motor imagery based on short-term entropy of time–frequency representations

 

cond

Accuracy (%)

TFR

tfrsp

tfrrsp

tfrgabor

tfrrgab

tfrpwv

tfrrpwv

tfrspwv

tfrrspwv

Feature type

Entropy

Entropy

Entropy

Entropy

Entropy

Entropy

Entropy

Entropy

Right vs up

VtG

51.06

53.37

53.43

52.86

54.49

55.24

52.22

52.56

noVtG

52.37

53.17

52.49

53.27

53.21

52.78

53.05

51.43

Right vs base

VtG

77.33

73.35

82.08

81.65

87.87

98.39

80.43

73.40

noVtG

75.80

71.30

80.94

84.08

89.02

98.78

81.39

70.76

Up vs base

VtG

74.66

71.10

80.74

82.40

87.30

98.44

79.04

69.60

noVtG

78.01

70.59

80.87

82.55

90.07

98.65

81.14

72.60

  

F1 score (%)

Right vs up

VtG

50.00

52.70

53.30

51.43

52.78

54.43

51.49

51.54

noVtG

51.41

52.76

51.87

52.41

53.30

51.45

52.58

50.63

Right vs base

VtG

76.79

72.25

81.41

80.03

85.93

98.29

79.56

72.75

noVtG

74.31

70.07

80.44

82.74

87.50

98.71

80.47

69.61

Up vs base

VtG

73.39

69.69

79.80

80.71

85.29

98.33

77.72

67.95

noVtG

77.03

69.27

80.20

81.17

88.65

98.55

80.03

71.96

  1. The best results for a certain type of feature are shown in bold