A Hybrid Approach Based on Variational Mode Decomposition for Analyzing and Predicting Urban Travel Speed

Table 2

Central period of modes of different K from speed data and reclassified modes with their spectral and statistical properties.

	Best K for link-day units			Reclassified modes
	8	10	12
	Period (hours) (min – max)	Period (hours) (min – max)	Period (hours) (min – max)		N	Period (hours)		% of variance
						(min – max)	CV	(min – max)
Mode 1	–	–	–	Mode 1	80	–	–	1–15
Mode 2	11.9–28.9	12.3–29.2	12.0–29.2	Mode 2	70	23.0–30.0	0.07	44–86
Mode 3	3.9–12.7	4.0–12.7	5.9–11.4	Mode 3	38	10.5–13.0	0.05	11–56
Mode 4	2.6–4.8	2.7–6.0	3.4–5.8	Mode 4	32	7.0–9.0	0.04	11–15
Mode 5	1.7–2.7	1.8–3.5	2.6–3.4	Mode 5	52	4.5–6.5	0.10	2–16
Mode 6	1.2–1.9	1.5–2.0	1.8–2.2	Mode 6	120	3.5–4.5	0.21	1–19
Mode 7	0.7–1.2	1.1–1.4	1.4–1.7	Mode 7	156	2.5–3.5	0.19	1–11
Mode 8	0.5–0.8	0.8–1.1	1.1–1.2	Mode 8	196	0–1.5	0.25	0–3
Mode 9	–	0.6–0.8	0.8–0.9
Mode 10	–	0.3–0.6	0.6–0.7
Mode 11	–	–	0.4–0.6
Mode 12	–	–	0.3–0.5