Skip to main content

Table 5 Performance of the classification rules based on single features and on the best subset of features

From: Nonlinear Heart Rate Variability features for real-life stress detection. Case study: students under stress due to university examination

Features

ACC

SEN

SPE

PPV

NPV

Classified as stress if

SD2

73%

79%

67%

70%

76%

SD2<0.0646

D 2

73%

69%

76%

74%

71%

D 2 <2.2533

REC

71%

67%

76%

74%

70%

REC>0.3791

En(r chon )

71%

64%

79%

75%

69%

En(r chon )<1.0530

α 1

71%

57%

86%

80%

67%

α 1 <1.2479

ShEn

68%

64%

71%

69%

67%

ShEn>3.3060

l mean

67%

57%

76%

71%

64%

l mean >13.2302

En(0.2)

64%

62%

67%

65%

64%

En(0.2)<1.0517

l max

60%

62%

57%

59%

60%

l max <250.6263

En(r max )

58%

64%

52%

57%

59%

En(r max )<1.1099

DET

56%

69%

43%

55%

58%

DET>0.9870

α 2

40%

50%

31%

42%

38%

α 2 <0.7711

SD1

39%

33%

45%

38%

40%

SD1>0.0243

SD1,SD2, En(0.2)

90%

86%

95%

95%

87%

See formula 15