A Higher-Order Motif-Based Spatiotemporal Graph Imputation Approach for Transportation Networks

Table 2

Analysis of the imputation with MGIA (10 min time interval). The acronyms “r-missing” and “c-missing” represent the patterns of random data missing and continuous data missing, respectively.

Pattern	Metrics	Missing rate
		0.1	0.2	0.3	0.4	0.5	0.6
r-missing	RMSE	0.0562	0.0622	0.0659	0.0746	0.0914	0.1176
c-missing	RMSE	0.0371	0.057	0.0631	0.0733	0.0759	0.0843
r-missing	MAE	0.0325	0.0501	0.0547	0.0581	0.0742	0.0938
c-missing	MAE	0.0292	0.0508	0.0535	0.0563	0.0653	0.0726
r-missing	MAPE	2.51%	3.81%	4.17%	4.27%	5.45%	6.95%
c-missing	MAPE	2.26%	3.94%	4.02%	4.2%	4.97%	5.45%