基于活动链聚类的居民出行方式选择影响因素分析

doi:10.3785/j.issn.1008-973X.2026.04.018

浙江大学学报(工学版)

2026, Vol. 60

Issue (4): 865-875 DOI: 10.3785/j.issn.1008-973X.2026.04.018

土木工程、交通工程

基于活动链聚类的居民出行方式选择影响因素分析

沈向诚1(

),孙轶琳1,2,*(

),谌淑杰2

1. 浙江大学建筑工程学院，浙江杭州 310058
2. 浙江大学工程师学院，浙江杭州 310058

Analysis of influencing factors on travel mode choice based on activity pattern clustering

Xiangcheng SHEN1(

),Yilin SUN1,2,*(

),Shujie CHEN2

1. College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, China
2. Polytechnic Institute of Zhejiang University, Hangzhou 310058, China

全文: PDF(3245 KB) HTML

摘要：

为了揭示居民单日活动链与出行时空要素对其出行方式选择的协同影响机制，基于出行调查数据，采用基于密度的噪声应用空间聚类（DBSCAN）方法对个体单日活动链进行时间切片重构与模式识别，提取出包含典型通勤模式（Home-Work-Home, HWH）在内的7类活动链特征. 在此基础上，构建轻量级梯度提升机（LightGBM）机器学习模型预测居民出行方式选择，并运用SHAP方法解析关键影响因素的作用机理. 研究发现：1）出行距离和时长是影响方式选择的核心决定因素； 2）HWH活动链与时空要素存在显著交互效应，表现为通勤群体在短时长（<40 min）中对公共交通的偏好程度显著低于其他群体，而在20~40 min出行时长区间内对电动自行车表现出更强的选择偏好，证实了活动链类型驱动的出行行为异质性特征.

关键词： 活动链; 出行方式选择; 机器学习; 通勤活动; DBSCAN聚类

Abstract:

The synergistic impact mechanism of residents’ daily activity patterns and spatio-temporal travel factors on their travel mode choice was investigated. Based on travel survey data, the density-based spatial clustering of applications with noise (DBSCAN) method was employed to perform time-slice reconstruction and pattern recognition of individuals’ daily activity patterns, extracting 7 activity pattern characteristics, including the typical Home-Work-Home (HWH) commute pattern. Subsequently, a light gradient boosting machine (LightGBM) machine learning model was constructed to predict residents’ travel mode choice, with the SHapley Additive exPlanations (SHAP) method used to interpret the mechanisms of key influencing factors. The findings revealed the following two key results: 1) Travel distance and duration were the core determinants of mode choice. 2) There was a significant interaction between the HWH pattern and spatio-temporal factors: compared to other groups, HWH commuters showed a lower preference for public transportation for trips under 40 min, yet a stronger preference for electric bicycles for trips between 20 and 40 min. These confirmed the activity pattern type-driven heterogeneity of travel behavior.

Key words: activity pattern travel mode choice machine learning commuting activities DBSCAN clustering

收稿日期: 2025-05-23 出版日期: 2026-03-19

CLC:

U 491.1

基金资助: 国家自然科学基金重点项目（52131202）；浙江省“尖兵”“领雁”研发攻关计划资助项目（2024C01214）.

通讯作者: 孙轶琳 E-mail: 22312303@zju.edu.cn;yilinsun@zju.edu.cn

作者简介: 沈向诚（2001—），男，硕士生，从事交通大数据研究. orcid.org/0009-0008-1345-6388. E-mail：22312303@zju.edu.cn

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	作者相关文章
	沈向诚
	孙轶琳
	谌淑杰

引用本文:

沈向诚,孙轶琳,谌淑杰. 基于活动链聚类的居民出行方式选择影响因素分析[J]. 浙江大学学报(工学版), 2026, 60(4): 865-875.

Xiangcheng SHEN,Yilin SUN,Shujie CHEN. Analysis of influencing factors on travel mode choice based on activity pattern clustering. Journal of ZheJiang University (Engineering Science), 2026, 60(4): 865-875.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2026.04.018 或 https://www.zjujournals.com/eng/CN/Y2026/V60/I4/865

表 1 居民出行调查基本信息示例

表 2 居民出行日志示例

图 1 出行调查数据个体属性分布

图 2 居民单日活动链重构

表 3 居民单日活动链示例

图 3 基于活动链聚类的轮廓系数热力图

图 4 居民单日活动链聚类

图 5 LightGBM模型和基准模型结果对比

图 6 基于SHAP值的出行方式选择的关键影响因素重要性及效应分析

图 7 出行距离-HWH（通勤）对出行方式选择的协同影响

图 8 出行时长-HWH（通勤）对出行方式选择的协同影响

图 9 年龄/收入-HWH（通勤）对出行方式选择的协同影响

1	KITAMURA R An evaluation of activity-based travel analysis[J]. Transportation, 1988, 15 (1): 9- 34 doi: 10.1007/bf00167973
2	HIDAYATI I, TAN W, YAMU C Conceptualizing mobility inequality: mobility and accessibility for the marginalized[J]. Journal of Planning Literature, 2021, 36 (4): 492- 507 doi: 10.1177/08854122211012898
3	DE DIOS ORTÚZAR J, WILLUMSEN L G. Modelling transport [M]. [S.l.]: John Wiley & Sons, 2024.
4	ZHOU Y, YUAN Q, YANG C, et al Who you are determines how you travel: clustering human activity patterns with a Markov-chain-based mixture model[J]. Travel Behaviour and Society, 2021, 24: 102- 112 doi: 10.1016/j.tbs.2021.03.005
5	DHARMOWIJOYO D B E, SUSILO Y O, KARLSTRÖM A Analysing the complexity of day-to-day individual activity-travel patterns using a multidimensional sequence alignment model: a case study in the Bandung Metropolitan Area, Indonesia[J]. Journal of Transport Geography, 2017, 64: 1- 12 doi: 10.1016/j.jtrangeo.2017.08.001
6	DIANAT A, HAWKINS J, HABIB K N Assessing the impacts of COVID-19 on activity-travel scheduling: a survey in the greater Toronto area[J]. Transportation Research Part A: Policy and Practice, 2022, 162: 296- 314 doi: 10.1016/j.tra.2022.06.008
7	MOECKEL R, HUANG W C, JI J, et al The activity-based model ABIT: modeling 24 hours, 7 days a week[J]. Transportation Research Procedia, 2024, 78: 499- 506 doi: 10.1016/j.trpro.2024.02.062
8	XIAO C, TANG J, LEE J J, et al Urban travel chain estimation based on combination of CHMM and LDA model[J]. IET Intelligent Transport Systems, 2025, 19: e70004 doi: 10.1049/itr2.70004
9	VO K D, LAM W H K, LI Z C A mixed-equilibrium model of individual and household activity-travel choices in multimodal transportation networks[J]. Transportation Research Part C: Emerging Technologies, 2021, 131: 103337 doi: 10.1016/j.trc.2021.103337
10	HUANG L, XIA F, CHEN H, et al Reconstructing human activities via coupling mobile phone data with location-based social networks[J]. Travel Behaviour and Society, 2023, 33: 100606 doi: 10.1016/j.tbs.2023.100606
11	HAFEZI M H, DAISY N S, MILLWARD H, et al Ensemble learning activity scheduler for activity based travel demand models[J]. Transportation Research Part C: Emerging Technologies, 2021, 123: 102972 doi: 10.1016/j.trc.2021.102972
12	KHAN N A, HABIB M A Microsimulation of activity generation, activity scheduling and shared travel choices within an activity-based travel demand modelling system[J]. Travel Behaviour and Society, 2023, 32: 100590 doi: 10.1016/j.tbs.2023.100590
13	LI Q, ZOU D, XU Y Combining individual travel behaviour and collective preferences for next location prediction[J]. Transportmetrica A: Transport Science, 2022, 18 (3): 1754- 1776 doi: 10.1080/23249935.2021.1968066
14	王江波, 连芝锐, 冯涛, 等基于机器学习的时空出行选择行为研究综述与展望[J]. 地理科学进展, 2024, 43 (8): 1649- 1665 WANG Jiangbo, LIAN Zhirui, FENG Tao, et al A review and outlook of machine learning-based travel choice behavior research[J]. Progress in Geography, 2024, 43 (8): 1649- 1665
15	FU X, ZHANG Y, DE DIOS ORTÚZAR J, et al Activity-travel pattern inference based on multi-source big data[J]. Transport Reviews, 2025, 45 (1): 26- 48 doi: 10.1080/01441647.2024.2400341
16	FU X, YAO Z, ZHANG Y, et al. Exploring variabilities of multi-week activity-travel patterns: a deep embedded clustering approach [J]. Transportation, 2025: 1–36.
17	WANG D, YANG M Gendered mobility and activity pattern: implications for gendered mental health[J]. Journal of Transport Geography, 2023, 110: 103639 doi: 10.1016/j.jtrangeo.2023.103639
18	LIU F, GAO Z, JANSSENS D, et al Identifying business activity-travel patterns based on GPS data[J]. Transportation Research Part C: Emerging Technologies, 2021, 128: 103136 doi: 10.1016/j.trc.2021.103136
19	付晓, 陈梓丹, 黄洁基于手机信令数据的城市居民非通勤出行群体画像: 以苏州市为例[J]. 地理科学, 2022, 42 (10): 1727- 1734 FU Xiao, CHEN Zidan, HUANG Jie Non-work travel group profiles of urban residents based on mobile phone signaling data: a case of Suzhou[J]. Scientia Geographica Sinica, 2022, 42 (10): 1727- 1734
20	HU Y, WEE B V, ETTEMA D Intra-household decisions and the impact of the built environment on activity-travel behavior: a review of the literature[J]. Journal of Transport Geography, 2023, 106: 103485 doi: 10.1016/j.jtrangeo.2022.103485
21	ARENTZE T A, TIMMERMANS H J P A need-based model of multi-day, multi-person activity generation[J]. Transportation Research Part B: Methodological, 2009, 43 (2): 251- 265 doi: 10.1016/j.trb.2008.05.007
22	WANG S, WU X, CHEN Y Association between perceived transportation disadvantages and opportunity inaccessibility: a social equity study[J]. Transportation Research Part D: Transport and Environment, 2021, 101: 103119 doi: 10.1016/j.trd.2021.103119
23	苏州市统计局. 苏州市第七次全国人口普查公报(第四号) [EB/OL]. (2021–05–31) [2025–04–27]. http://tjj.suzhou.gov.cn/sztjj/tjgb/202105/63f291317a62483ba1b6872b64b45b98.shtml.
24	YANG C, ZHANG Y, ZHAN X, et al Fusing mobile phone and travel survey data to model urban activity dynamics[J]. Journal of Advanced Transportation, 2020, 2020: 5321385 doi: 10.1155/2020/5321385
25	WANG W, OSARAGI T Generating and understanding human daily activity sequences using Time-Varying Markov Chain models[J]. Travel Behaviour and Society, 2024, 34: 100711 doi: 10.1016/j.tbs.2023.100711
26	LI W, ZHANG Y, CHEN Y, et al Multi-day activity pattern recognition based on semantic embeddings of activity chains[J]. Travel Behaviour and Society, 2024, 34: 100682 doi: 10.1016/j.tbs.2023.100682
27	何艳, 孙轶琳, 赵志健, 等融合碳激励潜变量的低碳出行方式选择模型[J]. 浙江大学学报: 工学版, 2024, 58 (8): 1628- 1635+1658 HE Yan, SUN Yilin, ZHAO Zhijian, et al Modeling low-carbon travel mode choice by incorporating carbon incentive latent variable[J]. Journal of Zhejiang University: Engineering Science, 2024, 58 (8): 1628- 1635+1658
28	LUNDBERG S M, LEE S I. A unified approach to interpreting model predictions [C]// Advances in Neural Information Processing Systems 30. Red Hook: Curran Associates Inc., 2017: 4768–4777.
29	XIONG J, XU L, WEI Z, et al Identifying, analyzing, and forecasting commuting patterns in urban public Transportation: a review[J]. Expert Systems with Applications, 2024, 249: 123646 doi: 10.1016/j.eswa.2024.123646

[1]	梅生启,李旭峰,王兴举,刘晓东,吴黎明,李星艳,刘哲. 基于机器学习的分形导数 Maxwell 混凝土徐变模型[J]. 浙江大学学报(工学版), 2026, 60(3): 487-494.
[2]	路庆昌,袁康洁. 空间异质性下共享单车出行量的非线性影响[J]. 浙江大学学报(工学版), 2025, 59(12): 2576-2584.
[3]	王冲,戴理朝,陈斌. 基于高斯过程回归的锈蚀RC梁抗剪承载力概率模型[J]. 浙江大学学报(工学版), 2025, 59(11): 2352-2360.
[4]	李昕阳,刘为锋,郭旭宁,李云玲,朱非林,钟平安. 流域风光水电出力互补特性[J]. 浙江大学学报(工学版), 2024, 58(7): 1505-1515.
[5]	李攀,周兵,柴天,邓园,潘倩兮,吴晓建. 考虑驾驶风格的车辆避障控制系统[J]. 浙江大学学报(工学版), 2024, 58(7): 1377-1386.
[6]	霍育福,金蓓弘,廖肇翊. 多模态信息增强的短视频推荐模型[J]. 浙江大学学报(工学版), 2024, 58(6): 1142-1152.
[7]	李素,陈泽,宋宝燕,张浩林. 营商环境评估的企业级复合区块链构建方法[J]. 浙江大学学报(工学版), 2024, 58(5): 891-899.
[8]	黄龙森,房俊,周云亮,郭志城. 基于变分自编码器的近似聚合查询优化方法[J]. 浙江大学学报(工学版), 2024, 58(5): 931-940.
[9]	高一聪,王彦坤,费少梅,林琼. 基于迁移学习的机械制图智能评阅方法[J]. 浙江大学学报(工学版), 2022, 56(5): 856-863, 889.
[10]	张鹏,田子都,王浩. 基于改进生成对抗网络的飞参数据异常检测方法[J]. 浙江大学学报(工学版), 2022, 56(10): 1967-1976.
[11]	黄发明,潘李含,姚池,周创兵,姜清辉,常志璐. 基于半监督机器学习的滑坡易发性预测建模[J]. 浙江大学学报(工学版), 2021, 55(9): 1705-1713.
[12]	任嘉豪,王海鸥,邢江宽,罗坤,樊建人. 湍流火焰切向应变率的低维近似模型[J]. 浙江大学学报(工学版), 2021, 55(6): 1128-1134.
[13]	战友,李强,马啸天,王郴平,邱延峻. 基于宏微观纹理特征融合的路面摩擦性能预测[J]. 浙江大学学报(工学版), 2021, 55(4): 684-694.
[14]	于勇,薛静远,戴晟,鲍强伟,赵罡. 机加零件质量预测与工艺参数优化方法[J]. 浙江大学学报(工学版), 2021, 55(3): 441-447.
[15]	陈巧红,陈翊,李文书,贾宇波. 多尺度SE-Xception服装图像分类[J]. 浙江大学学报(工学版), 2020, 54(9): 1727-1735.

Viewed

Full text

Abstract

Cited

Shared

Discussed