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 1 MV-GCN与基线模型的平均性能对比
Tab.1 Average performance comparison of MV-GCN and baseline models
模型MAEMSERMSERecall
SVR[12]6.4418119.740610.93090.5518
DTR[12]5.7394134.038411.56220.7222
RFR[4]4.127066.14588.11470.6166
GBR[12]4.351993.62569.66810.7592
BPNN[8]6.4668140.622711.84790.5056
XGB[13]4.494272.76748.51100.6648
DF-TAR[38]3.293030.88215.89110.8306
MV-GCN2.776022.24194.71580.9333