Examining the Impact of Different Periodic Functions on Short-Term Freeway Travel Time Prediction Approaches

Table 3

MAE, MAPE, and RMSE of six models for different minutes ahead predictions with 15-minute as aggregating level.

Time scale: 15 min		Minutes ahead predictions
MAE(s)	Model	5 min	10 min	15 min	30 min	45 min	60 min
Machine learning models	SVM	—	—	24.30	35.98	45.79	52.72
	BPNN	—	—	25.41	38.48	45.73	61.38
	MLR	—	—	37.14	68.42	88.75	106.79
Statistical models	ARIMA	—	—	32.64	56.16	65.82	79.20
	ST	—	—	30.47	49.01	60.88	68.28
	VAR	—	—	30.87	48.66	58.80	65.82
MAPE (%)	Model	5 min	10 min	15 min	30 min	45 min	60 min
Machine learning models	SVM	—	—	9.70	15.43	21.39	24.81
	BPNN	—	—	11.09	16.25	21.66	28.05
	MLR	—	—	20.99	39.86	51.47	62.47
Statistical models	ARIMA	—	—	18.19	33.01	37.99	48.02
	ST	—	—	15.55	24.54	31.12	35.59
	VAR	—	—	16.48	25.19	29.74	33.13
RMSE(s)	Model	5 min	10 min	15 min	30 min	45 min	60 min
Machine learning models	SVM	—	—	39.90	57.49	70.21	80.76
	BPNN	—	—	41.57	65.63	72.81	95.45
	MLR	—	—	49.56	85.06	112.00	130.03
Statistical models	ARIMA	—	—	45.50	75.91	90.63	106.43
	ST	—	—	45.06	71.97	91.30	100.50
	VAR	—	—	43.86	70.56	87.05	96.55

Bold values indicate the smallest MAE, MAPE, and RMSE values in machine learning models and statistical models, respectively.