Journal of Jilin University(Engineering and Technology Edition) ›› 2024, Vol. 54 ›› Issue (9): 2588-2599.doi: 10.13229/j.cnki.jdxbgxb.20221413

Previous Articles    

Recognition of travel patterns for urban rail transit passengers based on spatiotemporal sequence similarity

Na ZHANG1(),Feng CHEN2(),Jian-po WANG3,Ya-di ZHU2   

  1. 1.School of Resources Engineering，Xi'an University of Architecture and Technology，Xi'an 710055，China
    2.School of Civil Engineering，Beijing Jiaotong University，Beijing 100044，China
    3.School of Transportation Engineering，Chang'an University，Xi'an 710064，China
  • Received:2022-11-08 Online:2024-09-01 Published:2024-10-28
  • Contact: Feng CHEN E-mail:na_zhang@xauat.edu.cn;fengchen@bjtu.edu.cn

RICH HTML

 0   

PDF (PC)

118

Abstract:

Based on smart card data （SCD） of urban rail transit， a method was proposed to identify travel patterns by modeling the spatio-temporal sequences of individuals. Firstly， all stations visited by a passenger individual were extracted， and the similarity of stations was calculated in terms of inter-station travel frequency， inter-station distance， and the station activity duration， thus the main spatial activity areas of this individual were classified using a hierarchical clustering algorithm. Secondly， the spatio-temporal sequence was inferred based on the travel order of the individual， which is a set of discrete values characterizing the spatio-temporal state. PCA-KL and K-Means++ were used to extract the similarity sequence structure to identify passenger travel patterns. Finally， using one-month SCD as an example to identify passenger travel patterns for Xi'an rail transit. The results show that the complex passenger flow has five travel patterns， among which three typical travel patterns are macroscopic commuter travel behavior， accounting for 79% of the total passenger flow. Thus， the pattern identified based on the similarity of individuals' travel spatiotemporal sequences fully reflects the particularity and universality of the research method and it is highly operable for different cities.

Key words: transportation system engineering, urban rail transit, smart card data, spatiotemporal sequence, passenger travel pattern, commuting travel

CLC Number: 

  • U491.1

Table 1

Record of consecutive rail transit trips of a cardholder"

交易时间票卡ID

进站

时间

进站ID

出站

时间

出站ID
20181112710001***142215261144134249
20181112710001***173457333175812261
20181113710001***081228261083526245
20181113710001***144350245150500261
20181116710001***114607261121415241
20181116710001***173339241175452227
20181216710001***145417261151257249
20181216710001***171938249173958261

Fig.1

Flow of research method"

Fig.2

Example clustering on individuals′ OD stations"

Fig.3

Process of passenger spatial-temporal sequence inference based on trip records"

Fig.4

Visualization of month-sequence of activities for passenger"

Fig.5

Mapping from a neighbor-patch of a sample to a parametric feature vector"

Fig.6

Proportion of passengers under different cluster numbers on stations"

Table 2

Average activity time spent of different spatial areas"

项目空间区域状态编号其他状态编号
1234567…0-1-2
平均τ/%37.316.55.74.13.50.90.6…-29.4-

Fig.7

Average correlation of corresponding principal component pairs of 15 subsamples"

Table 3

Index evaluation with different K"

指标K值
2345678910
DBI3.062.6192.3242.1642.1012.0211.9481.9351.816
CH0.0910.1090.1130.1200.1180.1170.1160.1130.114
K值111213141516171819
DBI1.9271.8921.8861.8661.8731.8811.8531.8421.851
CH0.1140.1120.1050.1070.1080.1020.1020.1010.099

Fig.8

Travel pattern 1 sequence structure"

Fig.9

Travel pattern 2 sequence structure"

Fig.10

Travel pattern 3 sequence structure"

Fig.11

Other travel pattern sequence structures"

Table 4

Classification statistics of travel patterns"

类别名称

构成

集群

乘客量占比/%出行量占比/%时空特征出行特征总体描述
模式1固定时空强化出行1、418.521.5出行频次最高、时间稳定，典型居住地、工作地属通勤行为
模式2固定时空常规出行3、7、835.841.8出行频次稳定、时间稳定，典型居住地、工作地属通勤行为
模式3弹性时间无典型工作地出行2、1016.715.7出行频次不稳定、时间灵活；典型居住地、无典型工作地属通勤行为
模式4偶发性无规则出行5、611.611.7城轨辅助出行，无法判断非通勤行为
模式5随机时空出行917.49.3出行频次与时间均随机；无典型居住地、工作地非通勤行为
1 赵娟娟. 城市轨道交通乘客时空出行模式挖掘及动态客流分析[D].深圳:中国科学院大学深圳先进技术研究院,2017.
Zhao Juan-juan. Spatio-temporal travel pattern mining and dynamic passenger flow analysis in urban rail transit system[D]. Shenzhen: Shenzhen Institutes of Advance Technology, Chinese Academy of Sciences, 2017.
2 朱亚迪,陈峰,王子甲,等.基于概率图模型的乘客出行链提取方法[J].吉林大学学报:工学版,2019,49(1):60-65.
Zhu Ya-di, Chen Feng, Wang Zi-jia, et al. Passengers' trip chains extraction method based on probabilistic graph model[J]. Journal of Jilin University (Engineering and Technology Edition), 2019,49(1):60-65.
3 Ma X L, Wu Y J, Wang Y H, et al. Mining smart card data for transit riders' travel patterns[J]. Transportation Research Part C: Emerging Technologies, 2013, 36: 1-12.
4 Cui Z Y, Long Y. Perspectives on stability and mobility of transit passenger's travel behavior through smart card data[J]. IET Intelligent Transport Systems, 2019, 13(12):1761-1769.
5 彭飞,宋国华,朱珊.城市公共交通常乘客通勤出行提取方法[J].交通运输系统工程与信息,2021,21(2):158-165, 172.
Peng Fei, Song Guo-hua, Zhu Shan. A method for extracting commuting trips of frequent passengers in urban public transportation[J]. Journal of Transportation Systems Engineering and Information Technology, 2021,21(2):158-165, 172.
6 周航,陈学武.集时空聚类和指标筛选的公共交通通勤者识别[J].交通运输工程与信息学报,2022,20(1):89-97.
Zhou Hang, Chen Xue-wu. Public transportation commuter identification based on spatiotemporal clustering and index screening[J]. Journal of Transportation Engineering and Information, 2022,20(1):89-97.
7 Hagerstraand T. What about people in regional science [J]. Papers in Regional Science,1970, 24(1): 7-24.
8 Langlois G G, Koutsopoulos H N, Zhao J. Inferring patterns in the multi-week activity sequences of public transport users[J]. Transportation Research Part C, 2016, 64:1-16.
9 刘永鑫.基于多源数据融合的城市公交系统乘客出行模式挖掘及其应用研究[D].广州: 华南理工大学土木与交通学院, 2018.
Liu Yong-xin. Study on key technologies of transit passengers' travel pattern mining and applications based on multiple sources of data[D]. Guangzhou: School of Civil Engineering & Transportation, South China University of Technology, 2018.
10 Kieu L M, Bhaskar A, Chung E. Passenger segmentation using smart card data[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(3):1537-1548.
11 姚志刚,杨杰,王元庆.基于个体出行模式的公交乘客活动规律性度量[J].北京交通大学学报, 2022, 46(4): 68-75.
Yao Zhi-gang, Yang Jie, Wang Yuan-qing. Measurement of public transport passenger behavior regularity based on individual travel pattern[J]. Journal of Beijing Jiaotong University, 2022, 46(4): 68-75.
12 Joh C H, Arentze T, Timmermans H. Pattern recognition in complex activity travel patterns: comparison of Euclidean distance,signal-processing theoretical, and multidimensional sequence alignment methods[J]. Transportation Research Record, 2001, 1752(1):16-22.
13 Day W H E, Edelsbrunner H. Efficient algorithms for agglomerative hierarchical clustering methods[J]. Journal of Classification, 1984, 1: 7-24.
14 Ortega-Tong M A. Classification of London's public transport users using smart card data[D]. Cambridge, Massachusetts: Department of Civil and Environmental Engineering, Massachusetts Institute of Technology, 2013.
15 Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science, 2000, 290(5500): 2323-2326.
16 Tenenbaum J B, Silva V, Langford J C. A global geometric framework for nonlinear dimensionality reduction[J]. Science, 2000, 290(5500): 2319-2323.
17 Levada A L M. PCA-KL: a parametric dimensionality reduction approach for unsupervised metric learning[J]. Advances in Data Analysis and Classification, 2021, 15(4): 829-868.
18 Pham D T, Dimov S S, Nguyen C D. Selection of K in K-means clustering[J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2005, 219(1): 103-119.
19 2022年度中国主要城市共享单车/电单车骑行报告[R].北京: 中国城市规划设计研究院, 2022.
2022 Annual report on sharing bikes/motorcycle riding in major Chinese cities[R].Beijing: China Academy of Urban Planning & Design, 2022.
20 周世兵,徐振源,唐旭清. K-means算法最佳聚类数确定方法[J].计算机应用, 2010, 30(8): 1995-1998.
Zhou Shi-bing, Xu Zhen-yuan, Tang Xu-qing. Method for determining optimal number of clusters in K-means clustering algorithm[J]. Journal of Computer Applications, 2010, 30(8): 1995-1998.
21 Day W H E, Edelsbrunner H. Efficient algorithms for agglomerative hierarchical clustering methods[J]. Journal of Classification, 1984, 1(1): 7-24.
[1] Bo-song FAN,Chun-fu SHAO. Urban rail transit emergency risk level identification method [J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(2): 427-435.
[2] Jian-hua LI,Ze-ding WANG. Planning of urban car distributed charging pile point selection considering path time-consuming [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(8): 2298-2303.
[3] Jing WANG,Feng WAN,Chun-jiao DONG,Chun-fu SHAO. Modelling on catchment area and attraction intensity of urban rail transit stations [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(2): 439-447.
[4] Qing-yong WANG,Wei-qiang QU. Optimization algorithm of urban rail transit operation scheduling based on linear programming [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(12): 3446-3451.
[5] Wei ZHANG,Shu-pei ZHANG,Chong-en LUO,Sheng ZHANG,Guo-lin WANG. Collision avoidance trajectory planning for intelligent vehicles in emergency conditions [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(7): 1515-1523.
[6] ZHAO Xue-yu, YANG Jia-qi, PENG Ya-mei. Competitive and cooperative relationship evolution mechanism between urban rail transit and traditional bus [J]. 吉林大学学报(工学版), 2017, 47(3): 756-764.
[7] XU Cheng, QU Zhao-wei, TAO Peng-fei. Estimation of bicycle path capacity under mixed bicycle traffic flow [J]. 吉林大学学报(工学版), 2016, 46(1): 63-69.
[8] YAO Xiang-ming, ZHAO Peng, YU Dan-dan. Dynamic origin-destination matrix estimation for urban rail transit based on averaging strategy [J]. 吉林大学学报(工学版), 2016, 46(1): 92-99.
[9] WANG Zhong-yu, CAI Qing, WU Bing, LI Lin-bo. Queue length estimation for signalized intersections based on multi-source data [J]. 吉林大学学报(工学版), 2015, 45(4): 1088-1094.
[10] SHAO Min-hua, SUN Li-jun, SHAO Xian-zhi. Network location model of sensors and algorithm based on turning ratios [J]. 吉林大学学报(工学版), 2013, 43(06): 1476-1481.
[11] CAO Yang, ZHAO Shu-zhi, TIAN Qing-fei. Urban rail transit subsidy policy based on maximum welfare [J]. , 2012, (03): 618-622.
[12] ZHAO Shu-zhi, CAO Yang, TIAN Qing-fei. Urban rail transit scheduling decision based on information fusion [J]. 吉林大学学报(工学版), 2011, 41(增刊1): 85-88.
[13] JIA Hong-fei, CHEN Bin, LI Guo-wei, ZHANG Jing-shan. Collision avoidance method in pedestrian simulation based on blockade-angle [J]. 吉林大学学报(工学版), 2011, 41(6): 1577-1580.
[14] JIANG Gui-Yan, ZHANG Wei, CHANG An-De. Data organization method for traffic information acquisition system based on GPSequipped floating vehicle [J]. 吉林大学学报(工学版), 2010, 40(02): 397-0401.
[15] CAO Shou-hua,YUAN Zhen-zhou,ZHAO Dan. Queuing mechanism of passengers at exit stairs of urban rail transit [J]. 吉林大学学报(工学版), 2009, 39(06): 1463-1468.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright © Journal of Jilin University(Engineering and Technology Edition), All Rights Reserved.
Tel: +86-431-85095297　Fax: +86-431-85094074　E-mail: xbgxb@jlu.edu.cn
Powered by Beijing Magtech Co. Ltd