Table 9 The detailed results of the COM-Ms.

From: Fractal and chaotic map-enhanced grey wolf optimization for robust fire detection in deep convolutional neural networks

Algorithm

F24 (COM-M1)

F25 (COM-M2)

F26 (COM-M3)

F27(COM-M4)

F28 (COM-M5)

F29 (COM-M6)

IPM-GWO

AV

40.002

99.88

218.33

288.44

33.22

655.25

SD

549.33

45.73

46.33

76.63

41.11

256.32

p-value

0.0022

0.026

0.026

0.0184

0.0184

0.033

MMI-GWO

AV

19.44

95.36

215.32

386.73

44.75

692.01

SD

17.33

66.48

45.20

99.89

28.3254

188.12

p-value

0.033

0.0184

0.00053

0.026

0.0044

0.00133

RGWO

AV

27.25

77.33

209.44

275.01

36.25

132.55

SD

11.144

45.20

50.36

33.56

22.33

63.16

p-value

0.022

0.00401

0.0077

NA

0.00201

0.0111

GWO

AV

52.77

135.48

232.63

311.148

55.66

523.12

SD

48.33

76.26

63.77

96.22

23.12

86.40

p-value

0.0022

0.026

0.026

0.0184

0.0184

0.033

CLGWO

AV

17.55

55.33

152.25

288.44

21.66

423.11

SD

14.37

32.19

40.36

75.33

12.55

55.19

p-value

0.039

0.017

0.0111

0.0233

0.026

0.00127

CF-GWO

AV

7.22

21.77

140.75

275.28

9.44

103.11

SD

10.48

19.62

32.01

34.25

3.88

39.55

p-value

NA

0.213

NA

0.25

NA

NA