Skip to main content

Table 10 Performance indexes for the optimal subset and for each classification algorithm using leave-one-out style under fast walking speed

From: The impact of feature extraction and selection for the classification of gait patterns between ACL deficient and intact knees based on different classification models

Algorithm

Feature set

SEN (%)

SPF (%)

ACC (%)

PPV (%)

NPV (%)

MCC

SVM

Opitmal feature set shown in Table 2

92.54

89.55

91.04

89.86

92.31

0.821

KNN

Opitmal feature set shown in Table 2

74.63

85.57

80.10

83.80

77.13

0.606

NB classifier

Opitmal feature set shown in Table 2

61.19

46.27

53.73

53.25

54.39

0.076

Decision tree

Opitmal feature set shown in Table 2

82.59

79.10

80.85

79.81

81.96

0.617

ELA classifier

Opitmal feature set shown in Table 2

79.60

80.60

80.10

80.40

79.80

0.602

  1. Bold values to highlight the relevant numbers