Passenger Flow Scale Prediction of Urban Rail Transit Stations Based on Multilayer Perceptron (MLP)

Table 5

Model training accuracy analysis—average daily passenger flow.

	Working days				Nonworking days
	MAE	RMSE	MAPE (%)	R^2	MAE	RMSE	MAPE (%)	R^2
MLP	10945.76	14169.81	28.24	0.70	10249.49	13838.02	34.97	0.81
RBF	16141.67	19643.37	40.47	0.42	9363.49	13952.38	36.57	0.29
KNN	14938.37	19703.60	35.09	0.42	10132.86	13460.24	35.78	0.34
Multiple linear regression	12778.40	17631.87	28.86	0.53	9479.27	13856.82	31.52	0.30

Bold values are the values with the smallest errors in prediction results for each model under different scenarios.