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

Table 1

MAE, MAPE, and RMSE of six models for different minutes ahead predictions with 5-minute as aggregating level.

Time scale: 5 min		Minutes ahead predictions
MAE(s)	Model	5 min	10 min	15 min	30 min	45 min	60 min
Machine learning models	SVM	17.69	25.84	32.52	46.33	53.78	60.73
	BPNN	18.10	26.10	34.87	48.02	54.07	60.94
	MLR	20.21	34.01	46.32	74.53	95.71	111.05
Statistical models	ARIMA	19.80	31.13	40.56	57.02	65.98	77.50
	ST	19.37	29.86	38.40	51.22	63.41	73.79
	VAR	19.39	30.74	39.31	56.48	68.82	78.16
MAPE (%)	Model	5 min	10 min	15 min	30 min	45 min	60 min
Machine learning models	SVM	6.95	10.18	12.69	19.90	25.14	29.73
	BPNN	7.20	10.57	14.73	23.77	26.28	30.82
	MLR	9.38	17.66	25.16	43.13	55.28	64.55
Statistical models	ARIMA	9.42	15.90	21.66	32.78	38.26	45.21
	ST	8.73	14.30	19.21	25.38	32.34	38.60
	VAR	9.10	15.15	19.72	28.19	33.16	38.06
RMSE(s)	Model	5 min	10 min	15 min	30 min	45 min	60 min
Machine learning models	SVM	27.82	41.08	52.33	72.33	83.07	91.32
	BPNN	28.38	40.93	53.60	73.15	81.75	89.47
	MLR	29.67	46.96	61.95	92.99	118.52	134.65
Statistical models	ARIMA	28.99	44.47	56.80	77.89	92.55	108.58
	ST	28.93	43.57	55.60	73.85	94.27	108.50
	VAR	27.98	43.62	55.18	78.74	98.34	105.69