基于图神经网络的路面病害态势预测方法

马泽超,刘小明,夏汗青,王伟强,王久增,申海涛

Pavement distress situation prediction method based on graph neural network

Zechao MA,Xiaoming LIU,Hanqing XIA,Weiqiang WANG,Jiuzeng WANG,Haitao SHEN

表 6 改变GCN层数的性能对比结果

Tab.6 Performance comparison results for varying number of GCN layers

NG MAE MSE RMSE Recall 2 2.6232 21.0216 4.5801 0.9301 4 2.7190 23.9804 4.7967 0.9189 6 2.6109 21.1484 4.5941 0.9333 8 2.6374 21.5172 4.6337 0.9254 10 2.7117 23.3828 4.7969 0.9046