Dynamic Origin-Destination Matrix Estimation Based on Urban Rail Transit AFC Data: Deep Optimization Framework with Forward Passing and Backpropagation Techniques

Table 3

RMSE and RMSN of the estimation results.

Station index	Origin station		(%)
1	Andelibeijie	0.669	2.71
2	Andingmen	1.890	2.01
3	Beihaibei	0.541	2.57
4	Beijingzhan	2.347	2.61
5	Beixinqiao	0.871	3.07
6	Caishikou	0.831	2.78
7	Changchunjie	5.602	2.52
8	Chaoyangmen	2.002	3.24
9	Chegongzhuang	1.532	2.47
10	Chegongzhuangxi	1.076	2.36
11	Chongwenmen	3.475	2.14
12	Ciqikou	0.747	3.92
13	Dengshikou	0.805	3.42
14	Dongdan	0.864	3.05
15	Dongdaqiao	1.057	2.83
16	Dongsi	0.849	3.13
17	Dongsishitiao	1.644	2.91
18	Dongwuyuan	0.708	2.81
19	Dongzhimen	3.988	2.70
20	Fuchengmen	2.200	2.73
21	Fuxingmen	1.323	3.00
22	Guloudajie	1.738	1.94
23	Hepinglibeijie	1.337	2.19
24	Hepingmen	1.707	1.92
25	Jianguomen	1.627	2.98
26	Jishuitan	4.913	2.17
27	Lingjinghutong	0.692	3.00
28	Nanlishilu	1.111	2.46
29	Nanluoguxiang	0.624	2.66
30	Pinganli	0.905	2.36
31	Qianmen	2.716	2.62
32	Shishahai	0.431	3.23
33	Tiananmendong	0.634	3.65
34	Tiananmenxi	0.482	3.94
35	Wangfujing	0.771	3.82
36	Xidan	0.827	2.81
37	Xinjiekou	1.000	2.84
38	Xisi	0.601	3.11
39	Xizhimen	3.687	2.77
40	Xuanwumen	2.076	2.03
41	Yonganli	1.229	3.16
42	Yonghegong	1.571	2.39
43	Zhangzizhonglu	0.719	2.77
Avg.		1.545	2.79
Max.		5.602	3.94
Min.		0.431	1.92