Table 8 Model comparison on ternary classification task.

From: Graph attention and Kolmogorov–Arnold network based smart grids intrusion detection

Model

Acc (%)

Pre (%)

Rec (%)

F1 (%)

FNR (%)

GraphKAN

98.66

98.63

99.21

98.63

0.79

BGWO-EC42

97.77

97.39

95.24

96.27

4.76

RF-RBM43

94.30

95.10

92.10

90.30

7.90

Net_Stack44

97.45

–

–

–

–

SVM-ACO49

78.00

80.50

77.40

–

22.60

GA-RBF-SVM47

90.90

89.90

91.30

85.80

8.70

PSO-SVM50

85.70

86.50

83.10

–

16.90

  1. Significant values are in bold.
Back to article page