Skip to main content

Table 2 MA vs. MS vs. NC classification results: LDA trained on 10-dimensional feature set

From: Automatic single-trial discrimination of mental arithmetic, mental singing and the no-control state from prefrontal activity: toward a three-state NIRS-BCI

Participant Number

Proper Labels

Randomized Labels

 

AdjustedAccuracy1(%)

NC correct (%)

MA correct (%)

MS correct (%)

Adjusted Accuracy (%)

1

64.5 ± 6.9

65.6

64.3

63.6

32.7 ± 8.1

2 2

49.0 ± 7.8

55.4

55.6

36.1

33.1 ± 6.7

3 2

46.5 ± 8.0

48.1

54.2

37.2

31.8 ± 6.7

4 2

47.9 ± 5.5

51.7

54.7

37.4

32.7 ± 5.2

5

63.6 ± 6.5

60.0

69.1

61.6

33.4 ± 6.5

6

55.0 ± 6.0

54.5

63.0

47.5

32.4 ± 5.6

7

66.8 ± 5.8

67.6

71.4

61.3

33.4 ± 6.0

Mean (all participants):

56.2 ± 8.7

50.4

54.0

43.1

32.8 ± 0.58

Mean (Participants P1,P5-P7) 3

62.5 ± 5.1

61.9

67.0

58.5

33.0 ± 0.54

  1. 1The overall average classification accuracy, as well as all individual classification accuracies, are significantly greater than chance (α = 0.01)
  2. 2As expected for this participant, classification of MS is very near chance level.
  3. 3Participants for whom both MA vs NC and MS vs NC could be classified with accuracy significantly exceeding chance [16]. These participants were considered candidates for the MA vs MS vs NC classification problem.
Back to article page

BMC Research Notes

ISSN: 1756-0500

Contact us