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

Table 2

MAE, MAPE, and RMSE of six models for different minutes ahead predictions with 10-minute as aggregating level.

Time scale: 10 min		Minutes ahead predictions
MAE(s)	Model	5 min	10 min	15 min	30 min	45 min	60 min
Machine learning models	SVM	—	21.79	—	39.29	—	54.90
	BPNN	—	21.60	—	44.41	—	59.36
	MLR	—	30.32	—	71.39	—	109.57
Statistical models	ARIMA	—	29.32	—	62.79	—	86.27
	ST	—	26.88	—	51.55	—	71.44
	VAR	—	26.89	—	51.77	—	67.50
MAPE (%)	Model	5 min	10 min	15 min	30 min	45 min	60 min
Machine learning models	SVM	—	8.88	—	17.20	—	25.55
	BPNN	—	8.92	—	20.81	—	30.91
	MLR	—	15.51	—	41.05	—	64.00
Statistical models	ARIMA	—	14.93	—	36.55	—	50.69
	ST	—	12.44	—	26.19	—	37.60
	VAR	—	13.49	—	26.79	—	34.04
RMSE(s)	Model	5 min	10 min	15 min	30 min	45 min	60 min
Machine learning models	SVM	—	35.27	—	63.21	—	84.38
	BPNN	—	35.67	—	70.50	—	87.33
	MLR	—	41.98	—	89.53	—	132.75
Statistical models	ARIMA	—	41.49	—	83.54	—	115.66
	ST	—	40.09	—	72.82	—	104.54
	VAR	—	38.66	—	73.83	—	97.83