From: ASENN: attention-based selective embedding neural networks for road distress prediction
Method | RMSE | \(R^2\) | MAE | MAPE |
---|---|---|---|---|
Random forest [5] | 0.021 | 0.999 | 0.008 | 0.020 |
XGBoost [6] | 0.012 | 0.999 | 0.005 | 0.016 |
LightGBM [7] | 0.054 | 0.996 | 0.014 | 0.052 |
CatBoost [8] | 0.053 | 0.996 | 0.013 | 0.035 |
MLP [3] | 0.106 | 0.987 | 0.026 | 0.141 |
ResNet [14] | 0.040 | 0.998 | 0.022 | 0.114 |
FT-transformer [10] | 0.008 | 0.999 | 0.006 | 0.016 |
TabNet [9] | 0.048 | 0.997 | 0.035 | 0.145 |
Ours | 0.002 | 0.999 | 0.001 | 0.006 |