Table 6 Sensitivity analysis of dropout rate and removal ratio on the second air compressor. The overall best performance at dropout \(=0.3\), \(p=0.75\) (Accuracy=95.54%, F1-score=80.10%).

From: Early detection of air leakage in IoT-connected compressors using enhanced data sampling with deep learning

Dropout

0.35

0.55

0.75

0.90

0.95

Accuracy (%)

F1-score (%)

Accuracy (%)

F1-score (%)

Accuracy (%)

F1-score (%)

Accuracy (%)

F1-score (%)

Accuracy (%)

F1-score (%)

0.1

95.46

79.02

95.41

78.55

95.26

79.25

94.82

74.60

94.03

71.06

0.2

95.45

79.90

95.39

78.95

95.49

79.94

95.15

77.33

94.84

76.26

0.3

95.33

80.01

95.50

79.97

95.54

80.10

95.33

78.46

95.07

76.89

0.4

95.34

79.79

95.38

79.79

95.23

79.86

95.37

79.07

94.97

77.07

0.5

95.30

79.81

95.37

79.84

95.26

79.46

95.25

79.34

94.45

77.65

0.6

95.40

79.28

95.41

79.41

95.42

79.80

93.99

76.61

94.80

77.86

  1. Significant values are in [bold].