Table 1 Classification results of different algorithms with the mean probability value ensemble learning (-b) at the second-stage TsEL (unit: %)

DNN

96.73

94.60

90.27

76.47

89.52

ELM

97.08 ± 0.45

90.31 ± 0.92

85.75 ± 1.16

72.39 ± 1.18

86.38 ± 0.93

ELM-AE

97.68 ± 1.31

94.25 ± 1.53

92.28 ± 2.04

86.63 ± 1.43

92.71 ± 1.58

B-ELM-AE

99.08 ± 0.34

95.88 ± 0.49

94.93 ± 0.93

89.85 ± 0.85

94.93 ± 0.65

MC-ELM-AE-C

98.63 ± 0.46

95.88 ± 0.67

94.35 ± 0.86

87.90 ± 1.27

94.19 ± 0.82

MC-ELM-AE-TsEL-V

98.53 ± 0.52

95.63 ± 0.55

93.73 ± 0.91

88.33 ± 1.48

94.05 ± 0.86

MC-ELM-AE-TsEL-W

99.03 ± 0.34

96.55 ± 0.52

95.53 ± 0.92

89.08 ± 1.61

95.05 ± 0.85

B-MC-ELM-AE-C

99.08 ± 0.35

96.08 ± 0.69

94.65 ± 1.07

89.93 ± 1.19

94.94 ± 0.83

B-MC-ELM-AE-TsEL-V

99.15 ± 0.31

96.20 ± 0.42

95.10 ± 0.88

90.45 ± 0.93

95.23 ± 0.63

B-MC-ELM-AE-TsEL-W

99.45 ± 0.30

97.00 ± 0.46

96.15 ± 1.26

91.63 ± 1.29

96.06 ± 0.83