Predicting Freeway Traffic Crash Severity Using XGBoost-Bayesian Network Model with Consideration of Features Interaction

Table 3

Parameter verification of the crash severity nodes.

Variables		Parameter learning results
Road section type	Type of roadside protection facilities	Fatal traffic crashes
		The relative error	Absolute error	The real value	Bayes
1	1	0.0335	0.0142	0.4369	0.4227
	2	0.0002	0.0001	0.5555	0.5556
	3	0.0303	0.0187	0.6341	0.6154
	4	0.0124	0.0060	0.4866	0.4806
	5	0.0177	0.0138	0.7916	0.7778
	6	0.0000	0.0000	0.0000	0.0000
	7	0.1110	0.0666	0.6666	0.6000
2	1	0.0000	0.0000	0.3333	0.3333
	2	0.0000	0.0000	0.0000	0.0000
	3	0.1001	0.0455	0.5000	0.4545
	4	0.0689	0.0503	0.7800	0.7297
	5	0.0000	0.0000	0.0000	0.0000
	6	0.0000	0.0000	0.0000	0.0000
	7	0.0000	0.0000	1.0000	1.0000
3	1	0.0000	0.0000	0.2500	0.2500
	2	0.0000	0.0000	1.0000	1.0000
	3	0.0476	0.0286	0.5714	0.6000
	4	0.0661	0.0480	0.7731	0.7251
	5	0.0000	0.0000	0.0000	00.0000
	6	0.0554	0.0416	0.7916	0.7500
	7	0.0000	0.0000	1.0000	1.0000