Research Article

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

Table 3

Clustering results of national and provincial highway data when K = 4.

YearQuarterGroupTime of entering highwayGross weight of vehicle and goodsCategory of gross weightProportion of gross weight (%)Axis numberProportion of axis number (%)Overload rateProportion of vehicles (%)

2018110:00–1:00
4:00–10:00
53.9637 t –43 t1.5720.020.1440.36
30.75
43 t –49 t3.1844.59
50.29
Over 49 t95.25694.36
22:00–3:0081.75Over 49 t10030.240.699.51
41.93
50.6
697.22
311:0029.0218 t –27 t21.16225.610.139.56
27 t –36 t36.83343.64
36 t –37 t2.17430.76
37 t –43 t39.84
412:00–23:0053.1937 t –43 t2.7620.080.1240.57
43 t –49 t3.645.25
Over 49 t93.65693.11
210:00–8:0053.1437 t –43 t2.7620.010.1347.95
31.56
43 t –49 t3.6144.97
Over 49 t93.63692.91
29:00–13:0028.5318 t –27 t22.43226.580.128.73
27 t –36 t37.78344.84
36 t –37 t1.99428.58
37 t –43 t37.79
314:00–21:0051.9737 t –43 t4.7820.020.1432.99
33.26
43 t –49 t5.346.4
51.22
Over 49 t89.92689.09
422:00–23:0077.5Over 49 t10020.020.6210.33
30.58
2.56
50.32
696.52
310:00–8:0053.3737 t –43 t3.0620.010.1244.59
30.31
43 t –49 t4.0946.23
51.08
Over 49 t92.85692.37
29:00–15:0028.0118 t –27 t25.81230.120.118.36
27 t –36 t33.61337.33
36 t –37 t1.07432.55
37 t –43 t39.51
316:00–20:0053.4637 t –43 t2.5730.310.1241.12
43 t –49 t3.0944.61
Over 49 t94.3450.96
694.12
421:00–23:0088.53Over 49 t10041.550.825.93
698.45
410:00–8:0057.0543 t –49 t6.8120.20.2541.18
31.2
410.7
Over 49 t93.1952.010.2541.18
685.89
211:0097.4937 t –43 t48.45332.110.217.9
43 t –49 t3.73442.82
313:00–22:0057.0337 t –43 t0.5530.40.2330.47
43 t –49 t5.69412.03
Over 49 t93.7651.12
686.45
411:0097.4918 t –27 t0.2130.381.0210.45
42.52
Over 49 t99.7951.26
695.85
2019110:00–3:0075.63Over 49 t10042.50.5616.59
697.5
24:00–10:0051.3337 t –43 t8.73414.290.135.21
43 t –49 t7.48685.71
Over 49 t83.79
311:00–13:00
18:00–23:00
49.9937 t –43 t9.1330.720.0843.28
43 t –49 t8.52412.56
Over 49 t82.3551.21
685.51
414:00–17:0021.8418 t –27 t67.86272.730.114.92
27 t –36 t32.14327.27
210:00–3:0084.11Over 49 t10030.60.7533
42.4
697.01
24:00–5:0057.243 t –49 t3.1530.650.2431.67
410.34
Over 49 t96.8551.08
687.93
36:00–15:0034.5718 t –27 t9.84215.480.1721.41
27 t –36 t14.77317.42
37 t –43 t58.29467.1
43 t –49 t17.1
416:00–23:0050.4237 t –43 t23.931.510.1913.92
43 t –49 t11.95438.19
Over 49 t64.14660.30.1913.92
3122:00–1:00
7:00–13:00
39.8327 t –36 t4.2922.80.1629.29
36 t –37 t2.8638.41
37 t –43 t75485.98
43 t –49 t12.8662.8
Over 49 t5
24:00–5:00
14:00–18:00
55.37Over 49 t95.96690.910.2040.4655
32:00–3:0081.43Over 49 t10047.690.7213.18
692.31
40.2525.8718 t –27 t40257.140.2510.98
27 t –36 t60342.86
410:00–4:0078.89Over 49 t10031.960.727.45
47.84
690.2
25:00–7:0025.418 t –27 t48.53271.680.2917.38
27 t –36 t45.58326.32
36 t –37 t3.6342.01
37 t –43 t2.27
38:00–15:0050.1537 t –43 t16.3920.160.1963.71
35.88
43 t –49 t10.02422.57
50.39
Over 49 t73.59671
416:00–23:0051.7137 t –43 t13.75310.670.2511.47
43 t –49 t16.49417.78
Over 49 t69.7652.22
669.33

Clustering results of national and provincial highway data when K = 4 (1). Clustering results of national and provincial highway data when K = 4 (2). Clustering results of national and provincial highway data when K = 4 (3). Clustering results of national and provincial highway data when K = 4 (4). Clustering results of national and provincial highway data when K = 4 (5). Clustering results of national and provincial highway data when K = 4 (6)