Analysis and Prediction of Overloaded Extra-Heavy Vehicles for Highway Safety Using Machine Learning

Table 2

Clustering results of expressway data at K = 6.

Group	Time of entering highway	Gross weight of vehicle and goods	Category of gross weight	Proportion of gross weight (%)	Axis number	Proportion of axis number (%)	Overload rate	Proportion of vehicles (%)
1	23:00–4:00	90.62	Over 49 t	100.00	6	100.00	0.85	1.16
2	5:00	53.11	43 t–49 t	2.43	3	0.50	0.11	50.83
					4	3.69
			Over 49 t	97.57	5	4.25
					6	90.58
					9	0.97
3	6:00–7:00 15:00–16:00	21.64	18 t–27 t	80.66	2	86.68	0.13	5.21
			27 t–36 t	19.34	3	13.32
4	8:00–11:00	41.88	27 t–36 t	2.37	3	14.59	0.17	6.72
			36 t–37 t	1.17	4	70.94
			37 t–43 t	55.47	5	11.39
			43 t–49 t	40.99	9	3.08
5	12:00–14:00	67.04	Over 49 t	100.00	4	1.40	0.38	9.70
					5	0.33
					6	97.62
					9	0.66
6	17:00–22:00	58.44	Over 49 t	100.00	4	0.73	0.20	26.38
					5	0.91
					6	97.88
					9	0.48