基于手机GPS数据的个体出行链提取方法研究

doi:10.16097/j.cnki.1009-6744.2023.05.005

交通运输系统工程与信息 ›› 2023, Vol. 23 ›› Issue (5): 45-54.DOI: 10.16097/j.cnki.1009-6744.2023.05.005

• 智能交通系统与信息技术 • 上一篇下一篇

基于手机GPS数据的个体出行链提取方法研究

周洋^{1, 2}，杨超^{2, 3}，郭唐仪^*1

1. 南京理工大学，自动化学院，南京 210094；2. 同济大学，交通运输工程学院，上海 201804； 3. 同济大学，城市交通研究院，上海 200092

收稿日期:2023-07-12 修回日期:2023-08-05 接受日期:2023-08-08 出版日期:2023-10-25 发布日期:2023-10-22
作者简介:周洋(1991- )，男，湖北荆州人，博士后。
基金资助:
国家重点研发计划(2019YFE0213800)；南京市国际合作项目(202002013)。

Inferring Individual Trip Chains from Smartphone-based GPS Data

ZHOU Yang^1,2,YANG Chao^2,3,GUO Tang-yi^*1

1. School of Automation, Nanjing University of Science and Technology, Nanjing 210094, China; 2. College of Transportation Engineering, Tongji University, Shanghai 201804, China; 3. Urban Mobility Institute, Tongji University, Shanghai 200092, China

Received:2023-07-12 Revised:2023-08-05 Accepted:2023-08-08 Online:2023-10-25 Published:2023-10-22
Supported by:
National Key Research and Development Program of China (2019YFE0213800)； Nanjing International Cooperative Project (202002013)。

摘要/Abstract

摘要： 针对现状出行数据存在的人工获取成本高、时空信息不准确及出行链接不完整等问题，开发智能手机居民出行调查系统，研究基于手机GPS数据的全时段、多交通方式且完整链接的个体出行链提取方法。首先，应用时空密度聚类方法，识别个体轨迹中的停驻点，构建随机森林模型，从停驻点中区分出行端点；其次，以空间邻近匹配方法识别居家与工作活动，利用家庭和个人属性、活动时空与活动链等特征，以XGBoost模型推断非家非工作类型的出行目的；最后，采用轨迹微分方法，提取运动特征、出行特征与GIS特征，运用XGBoost模型推断出行方式。利用出行调查系统采集的实验数据，验证出行链提取方法。结果表明：停驻点识别查准率和查全率分别为96.7%和96.4%，出行端点查准率为97.6%，公交换乘点查准率为91.8%；出行目的推断上，“居家/回家”准确率为100%，“上班/上学”准确率为89.8%，非家非工作出行目的综合准确率为87.6%；出行方式推断上，各交通方式准确率均达到 90%以上，综合准确率为 95.0%。本文提供一种手机GPS轨迹数据的出行链挖掘方法，能够为智能手机居民出行调查现实应用提供支撑。

关键词: 城市交通, 出行链, XGBoost, GPS数据, 出行调查

Abstract: To address the limitations of current travel data, such as high-labor cost, inaccuracy in time and location, and missing trips, we develop a smartphone-based travel survey system and propose a method for inferring individual trip chains from smartphone GPS data with all-period, multimodal, and complete trips. Firstly, anchors are extracted from personal trajectories with a proposed spatiotemporal density-based clustering algorithm. The anchors are then classified into public transport transfer nodes and trip ends using a random forest model. Secondly, a spatial proximity matching method is used to identify residential and commuting activities. An XGBoost model is built with household and personal attributes, activity chain, and spatiotemporal characteristics. The model is employed to classify the types of non-home-non-work activities. Thirdly, we cut trip trajectory into trip slices and extract features referred to motion, trip, and GIS data, and infer travel mode by the XGBoost model. The proposed trip chain inference method is validated with an experimental dataset collected by travel survey system. Results show that the precision and recall of anchors extraction are 96.7% and 96.4%, respectively; the precision of identifying trip ends and public transport transfer nodes are 97.6% and 91.8%, respectively. For trip purpose inference, the model achieves accuracies of 100% for home, 89.8% for work/education, and 87.6% for non-home-non-work activities. For travel mode inference, each mode gets an accuracy of over 90%, and the comprehensive accuracy reaches 95.0%. This paper provides a method of mining trip chains from GPS trajectory to support the application of smartphone-based household travel surveys in the real world.

Key words: urban traffic, trip chain, XGBoost, GPS data, travel survey

中图分类号:

U121

周洋, 杨超, 郭唐仪. 基于手机GPS数据的个体出行链提取方法研究[J]. 交通运输系统工程与信息, 2023, 23(5): 45-54.

ZHOU Yang, YANG Chao, GUO Tang-yi. Inferring Individual Trip Chains from Smartphone-based GPS Data[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(5): 45-54.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2023.05.005

http://www.tseit.org.cn/CN/Y2023/V23/I5/45

参考文献

[1] ZHANG M, LI Y. Generational travel patterns in the United States: New insights from eight national travel surveys[J]. Transportation Research Part A: Policy and Practice, 2022, 156: 1-13.

[2] SHEN L, STOPHER P R. Review of GPS travel survey and GPS data-processing methods[J]. Transport Reviews, 2014, 34(3): 316-334.

[3] 肖光年, 隽志才, 高晶鑫. 基于GPS定位数据的出行端点推断[J]. 吉林大学学报(工学版), 2016, 46(3): 770- 776. [XIAO G N, JUAN Z C, GAO J X. Inference method of trip ends based on GPS track data[J]. Journal of Jilin University (Engineering and Technology Edition), 2016, 46(3): 770-776.]

[4] YANG Y, JIA B, YAN X, et al. Identifying intercity freight trip ends of heavy trucks from GPS data[J]. Transportation Research Part E: Logistics and Transportation Review, 2022, 157: 102590.

[5] YAO Z, YANG F, GUO Y, et al. Trip end identification based on spatial-temporal clustering algorithm using smartphone positioning data[J]. Expert Systems with Applications, 2022, 197: 116734.

[6] YANG F, YAO Z, CHENG Y, et al. Multimode trip information detection using personal trajectory data[J]. Journal of Intelligent Transportation Systems, 2016, 20 (5): 449-460.

[7] RASMUSSEN T K, INGVARDSON J B, HALLDÓRSDÓTTIR K, et al. Improved methods to deduct trip legs and mode from travel surveys usingwearable GPS devices: A case study from the Greater Copenhagen area[J]. Computers, Environment and Urban Systems, 2015, 54: 301-313.

[8] ZHOU X, YU W, SULLIVAN W C. Making pervasive sensing possible: Effective travel mode sensing based on smartphones[J]. Computers, Environment and Urban Systems, 2016, 58: 52-59.

[9] 姚振兴, 许心越, 邵海鹏, 等. 基于手机 GPS 定位数据的交通方式换乘点识别方法研究[J]. 中国公路学报, 2021, 34(12): 276-287. [YAO Z X, XU X Y, SHAO H P, et al. Method for traffic mode transfer behavior identification by busing smartphone GPS data[J]. China Journal of Highway Transport, 2021, 34(12): 276-287.]

[10] BALLI S, SAĞBAŞ E A. Diagnosis of transportation modes on mobile phone using logistic regression classification[J]. IET Software, 2018, 12(2): 142-151.

[11] YANG M, PAN Y, DARZI A, et al. A data-driven travel mode share estimation framework based on mobile device location data[J]. Transportation, 2022, 49(5): 1339-1383.

[12] WANG C, LUO H, ZHAO F, et al. Combining residual and LSTM recurrent networks for transportation mode detection using multimodal sensors integrated in smartphones[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22(9): 5473-5485.

[13] XIAO G, JUAN Z, ZHANG C. Detecting trip purposes from smartphone-based travel surveys with artificial neural networks and particle swarm optimization[J]. Transportation Research Part C: Emerging Technologies, 2016, 71: 447-463.

[14] ERMAGUN A, FAN Y, WOLFSON J, et al. Real-time trip purpose prediction using online location-based search and discovery services[J]. Transportation Research Part C: Emerging Technologies, 2017, 77: 96- 112.

[15] 宗芳, 齐厚成, 唐明, 等. 基于 GPS 数据的日出行模式 - 出行目的识别 [J]. 吉林大学学报 ( 工学版), 2018, 48(5): 1374-1379. [ZONG F, QI H C, TANG M, et al. Identifying daily travel pattern-trip purpose using GPS data[J]. Journal of Jilin University (Engineering and Technology Edition), 2018, 48(5): 1374-1379.]

[16] 周洋, 杨超. 基于时空聚类算法的轨迹停驻点识别研究[J]. 交通运输系统工程与信息, 2018, 18(4): 88-95. [ZHOU Y, YANG C. Anchor identification in trajectory based on temporospatial clustering algorithm[J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(4): 88-95.]

[17] 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.

[18] CHEN T, GUESTRIN C. Xgboost: A scalable tree boosting system[C]//In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016. [19] SCHUESSLER N, AXHAUSEN K W. Processing raw data from global positioning systems without additional information[J]. Transportation Research Record, 2009, 2105(1): 28-36.

基于手机GPS数据的个体出行链提取方法研究

Inferring Individual Trip Chains from Smartphone-based GPS Data

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	邓毛颖, 邓策方. 基于结构、效率、公平与韧性的路网密度适宜性评价研究[J]. 交通运输系统工程与信息, 2023, 23(6): 22-32.
[2]	荆彬彬, 林永杰, 阎珠豪, 黄政杰. 非闭合交通路网路径选择与绿波协调同步优化方法[J]. 交通运输系统工程与信息, 2023, 23(6): 51-62.
[3]	张兵, 陶文康, 刘建荣, 薛运强, 邓明君. 有限理性视域下老年人出行方式选择巢式Logit模型[J]. 交通运输系统工程与信息, 2023, 23(6): 74-82.
[4]	彭金栓, 袁浩, 宋臻, 范子斌, 杨祥浩, 张磊. 等待阶段使用手机对行人过街风险的影响[J]. 交通运输系统工程与信息, 2023, 23(6): 83-89.
[5]	张文会, 徐海彬, 周舸, 温文. 信控交叉口行人过街冲突严重程度评价模型[J]. 交通运输系统工程与信息, 2023, 23(6): 89-99.
[6]	王伊凡, 陈学武. 考虑空间效应的公交站点客流量影响因素分析[J]. 交通运输系统工程与信息, 2023, 23(6): 153-164.
[7]	高良鹏, 郑乐, 简文良, 马新卫, 季彦婕. 弹性激励下多停车场共享泊位竞价有效权分配算法[J]. 交通运输系统工程与信息, 2023, 23(6): 176-184.
[8]	肖雅玲, 柏赟, 陈垚, 李竹君, 温芳. 考虑车底运用的城轨货运专列运行图与载货方案协同优化[J]. 交通运输系统工程与信息, 2023, 23(6): 185-195.
[9]	王培恒, 杨立兴, 李树凯, 高自友. 考虑换乘站客流疏解的地铁列车跳站与客流控制协同优化[J]. 交通运输系统工程与信息, 2023, 23(6): 196-205.
[10]	庞磊, 任利剑, 运迎霞. 建成环境对轨道交通站点客流量与通勤乘车率影响的差异化分析[J]. 交通运输系统工程与信息, 2023, 23(6): 206-214.
[11]	户佐安, 邓锦程, 杨江浩, 赵妍. 轨道交通站点聚类及其对客流预测的影响分析[J]. 交通运输系统工程与信息, 2023, 23(6): 227-238.
[12]	张燕, 李子鑫, 刘进平. 考虑工作量平衡的餐饮垃圾多行程收运路线优化[J]. 交通运输系统工程与信息, 2023, 23(6): 239-249.
[13]	马利, 付锐, 孙秦豫, 郭应时, 王畅, 袁伟. 不同情境下乘员对车辆运动参数的晕车敏感性研究[J]. 交通运输系统工程与信息, 2023, 23(6): 284-295.
[14]	胡宝雨, 刘学. 基于手机信令数据的城市区域居民出行OD预测模型[J]. 交通运输系统工程与信息, 2023, 23(6): 296-306.
[15]	高万晨, 路世昌, 李丹. 基于智能刷卡数据的乘客上车站点估计研究[J]. 交通运输系统工程与信息, 2023, 23(6): 307-318.