Table 7 Ternary classification accuracy on multiple subsets.
From: Graph attention and Kolmogorov–Arnold network based smart grids intrusion detection
Subset | GCN-FC (%) | GAT-FC (%) | KAN-MLP (%) | GraphKAN (%) |
|---|---|---|---|---|
1 | 97.08 | 98.53 | 98.00 | 98.99 |
2 | 93.65 | 98.66 | 97.88 | 98.21 |
3 | 97.01 | 99.09 | 98.36 | 98.62 |
4 | 95.18 | 97.79 | 97.61 | 98.33 |
5 | 94.43 | 98.95 | 97.44 | 98.92 |
6 | 94.00 | 98.32 | 97.74 | 97.95 |
7 | 97.47 | 99.05 | 98.06 | 98.27 |
8 | 96.47 | 98.47 | 98.06 | 99.43 |
9 | 93.72 | 97.47 | 96.07 | 97.78 |
10 | 95.61 | 98.69 | 98.07 | 98.87 |
11 | 96.06 | 99.11 | 98.04 | 99.31 |
12 | 95.61 | 97.71 | 97.34 | 98.68 |
13 | 97.13 | 99.09 | 97.71 | 99.13 |
14 | 96.08 | 98.07 | 98.24 | 98.71 |
15 | 95.81 | 97.31 | 97.16 | 97.26 |
