Journal of Big Data

Table 7 The compared results on the rutting dataset

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

Back to article page