MDGCN: Multiple Graph Convolutional Network Based on the Differential Calculation for Passenger Flow Forecasting in Urban Rail Transit

Table 4

The evaluation results of spatial relationship reconstruction.

Model	SH
	RMSE			MAE
	10 min	15 min	30 min	10 min	15 min	30 min
MDGCN-A	35.548	30.674	29.541	19.066	16.078	15.597
MDGCN-AD	25.685	35.547	36.545	14.950	16.635	18.654
MDGCN-AC	20.365	26.654	23.315	11.027	14.028	12.389
MDGCN	17.041	20.962	22.354	10.552	12.786	13.452
Model	XM
	RMSE			MAE
	10 min	15 min	30 min	10 min	15 min	30 min
MDGCN-A	27.241	27.624	30.148	18.279	18.698	23.039
MDGCN-AD	22.148	55.512	27.539	14.208	26.384	14.257
MDGCN-AC	18.214	19.012	22.351	10.852	11.109	13.691
MDGCN	16.713	16.927	18.560	9.924	10.247	11.155