Table 4 The generation indexes of different methods.
From: Predicting road traffic accident severity from imbalanced data using VAE attention and GCN
Datasets | Index | Different generation methods | ||||
|---|---|---|---|---|---|---|
GAN | VAE | DCGAN | ADASYN | Ours | ||
NEWYORK | JSD | 0.5658 | 0.6177 | 0.6777 | 0.0941 | 0.1887 |
KLD | 5.5123 | 4.438 | 19.92064 | 0.0248 | 0.1395 | |
WD | 0.2204 | 0.5402 | 4.52902 | 0.2313 | 0.2640 | |
CHILI | JSD | 0.6495 | 0.7365 | 0.6825 | 0.1516 | 0.1969 |
KLD | 3.2424 | 3.0344 | 19.7025 | 0.0637 | 0.2004 | |
WD | 0.2931 | 0.844 | 3.94 | 0.2740 | 0.2477 | |
BRONX | JSD | 0.5049 | 0.6065 | 0.6382 | 0.1540 | 0.1817 |
KLD | 4.6350 | 5.5614 | 19.378 | 0.0597 | 0.1457 | |
WD | 0.1947 | 0.4118 | 4.2162 | 0.4378 | 0.2456 | |
