Table 10 Model comparison on 37-class classification task.

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

Model

Acc(%)

Pre(%)

Rec(%)

F1(%)

FNR(%)

GraphKAN

99.04

98.99

99.57

99.00

0.43

RF-RBM43

94.30

–

–

–

–

Net_Stack44

95.52

–

–

–

–

DDPM-LGBM

94.44

92.49

92.46

92.47

7.54

DenseNet-BC

90.79

89.82

89.42

89.56

10.58

Conv1D

85.27

84.49

83.65

83.95

16.35

KNN

81.81

79.63

79.70

79.66

20.30

RNN

86.79

85.06

85.13

83.49

14.87

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