基于手机信令的城市机动化方式细分双层模型研究

doi:10.16097/j.cnki.1009-6744.2023.03.012

交通运输系统工程与信息 ›› 2023, Vol. 23 ›› Issue (3): 101-109.DOI: 10.16097/j.cnki.1009-6744.2023.03.012

• 智能交通系统与信息技术 • 上一篇下一篇

基于手机信令的城市机动化方式细分双层模型研究

郭煜东¹，杨飞^*1，周涛²，姚振兴³，张楚良¹，魏胤呈⁴

1.西南交通大学，交通运输与物流学院，成都611756；2.重庆市交通规划研究院，重庆401147；3.长安大学，运输工程学院，西安710064；4.香港大学，统计及精算学系，香港999077

收稿日期:2023-01-21 修回日期:2023-04-26 接受日期:2023-04-28 出版日期:2023-06-25 发布日期:2023-06-23
作者简介:郭煜东(1994-)，男，重庆奉节人，博士生
基金资助:
国家自然科学基金(52072313, 52002030)；教育部人文社会科学基金 (20XJCZH011)

Two-layer Model to Distinguish Urban Motorized Travel Mode Based on Mobile Phone Signaling Data

GUO Yu-dong¹, YANG Fei^*1, ZHOU Tao², YAO Zhen-xing³, ZHANG Chu-liang¹, WEI Yin-cheng⁴

1. Department of Transportation and Logistics, Southwest Jiaotong University, Chengdu 611756, China; 2. Chongqing Transport Planning Institute, Chongqing 401147, China; 3. College of Transportation Engineering, Chang'an University, Xi'an 710064, China; 4. Department of Statistics and Actuarial Science, University of Hong Kong, Hong Kong 999077, China

Received:2023-01-21 Revised:2023-04-26 Accepted:2023-04-28 Online:2023-06-25 Published:2023-06-23
Supported by:
National Natural Science Foundation of China(52072313, 52002030)；Humanities and Social Sciences Foundation of the Ministry of Education of China (20XJCZH011)

摘要/Abstract

摘要： 针对现阶段手机信令数据难以适用城市复杂出行环境，无法有效区分密集路网下机动化出行方式，本文提出一种考虑路径精准拟合与多维时空特征的双层识别模型。在出行路径识别层面，Savitzky-Golay(S-G)滤波能有效平滑信令数据相对实际出行路径的波动，线性插值算法能弥补信令数据时空缺失。在出行方式识别层面，探究了识别路径相似度、出行时间相似度、加速度、小波速度等关键因素，利用K-临近算法识别公交、小汽车。结果表明：本文提出方法能有效细分城市密集路网环境下的公交与小汽车出行，识别准确度分别达到88.29%和82.28%。在不同出行距离、出行时段、拥挤状态、道路等级、道路类型及识别路径相似度等角度，识别效果均优于随机森林等算法。研究支撑了基于信令数据的出行特征精准挖掘，为道路规划建设，公交线网规划等提供重要基础。

关键词: 智能交通, 机动化方式细分, 双层模型, 手机信令数据, 密集道路网络

Abstract: It is always difficult to apply the mobile phone signaling data in the actual urban complex travel environment and also challenging to distinguish the motorized travel mode under dense road networks. This paper proposes a twolayer model considering accurate path fitting and multidimensional spatio-temporal characteristics. At the level of travel path identification, S- G filtering can effectively smooth signaling data fluctuation relative to the actual travel path. The linear interpolation algorithm can fill in the time and space gaps. At the level of travel mode recognition, the key factors are mined, including the similarity of the recognized travel path, travel time similarity, acceleration, and wavelet velocity. The K-nearest neighbor algorithm is used to identify the travel modes (by car or bus). The results show that the proposed method can effectively identify the bus and car in the dense urban road network, and the accuracy rates can reach 88.29% and 82.28% , respectively. Under different travel distances, travel time, congestion conditions, road classes, road types, and path similarity, the proposed method is better than the existing algorithms, such as random forest, in the accuracy rate. The research supports the accurate recognition of travel characteristics based on mobile phone signaling data. It also provides an essential basis for road planning, construction, and public transit network planning.

Key words: intelligent transportation, motorized travel mode distinguishment, two-layer model, mobile phone signaling data, dense road network

中图分类号:

U491.1

郭煜东, 杨飞, 周涛, 姚振兴, 张楚良, 魏胤呈. 基于手机信令的城市机动化方式细分双层模型研究[J]. 交通运输系统工程与信息, 2023, 23(3): 101-109.

GUO Yu-dong, YANG Fei, ZHOU Tao, YAO Zhen-xing, ZHANG Chu-liang, WEI Yin-cheng. Two-layer Model to Distinguish Urban Motorized Travel Mode Based on Mobile Phone Signaling Data[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(3): 101-109.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2023.03.012

http://www.tseit.org.cn/CN/Y2023/V23/I3/101

参考文献

[1] GONZÁLEZ M C, HIDALGO C A, BARABASI A L. Understanding individual human mobility patterns[J]. Nature, 2008, 453 (7196): 779-782.

[2]王垚, 钮心毅, 宋小冬. 基于城际出行的长三角城市群空间组织特征[J]. 城市规划, 2021, 45(11): 43-53. [WANG Y, NIU X Y, SONG X D. Spatial organizational characteristics of the yangtze river delta urban agglomeration based on intercity trips[J]. City Planning Review, 2021, 45(11): 43-53.]

[3] HOTEIT S, SECCI S, SOBOLEVSKY C, et al. Estimating human trajectories and hotspots through mobile phone data[J]. Computer Networks, 2014, 64: 296-307.

[4] LI M X, GAO S, LU F et al. Reconstruction of human movement trajectories from large-scale low-frequency mobile phone data[J]. Computers, Environment and Urban Systems, 2019, 77: 101346.

[5] YANG F, YAO Z X, JIN J P, et al. Performance evaluation of handoff-based cellular traffic monitoring systems using combined wireless and traffic simulation platform[J]. Journal of Intelligent Transportation Systems, 2016, 20(2): 113-124. [6] QIAO S J, SHEN D Y, WANG X T, et al. A self-adaptive parameter selection trajectory prediction approach via hidden markov models[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(1): 284-296.

[7] BACHIR D, KHODABANDELOU G, GAUTHIER V, et al. Inferring dynamic origin-destination flows by transport mode using mobile phone data[J]. Transportation Research Part C: Emerging Technologies, 2019, 101: 254-275.

[8] WANG L L, YANG F, JIN J P, et al. Detection of traffic pattern based on fuzzy clustering and wavelet analysis model at different signaling positioning frequencies[J]. Transportation Research Record, 2022, 2676(8), 601-618.

[9] CHEN J T, XIONG C, CAI M. A travel mode identification framework based on cellular signaling data[J]. Mobile Information Systems, 2022: 2113213.

[10] PENG Z H, BAI G K, WU H, et al. Travel mode recognition of urban residents using mobile phone data and mapAPI[J]. Environment and Planning B: Urban Analytics and City Science, 2021, 48(9): 2574-2589.

[11] CHEN X X, XU X D, YANG C. Trip mode inference from mobile phone signaling data using logarithm gaussian mixture model[J]. Transportation Research Part C: Emerging Technologies, 2020, 13(1): 429-445.

[12] CHEN H K, HO H C, WU L Y et al. Two-stage procedure for transportation mode detection based on sighting data[J]. Transportmetrica A: Transport Science, 2022, 1:1-35.

[13] LU Z B, LONG Z, XIA J X, et al. A random forest model for travel mode identification based on mobile phone signaling data[J]. Sustainability, 2019, 11(21): 1-21.

[1]	陈峥, 赵文龙, 郭凤香, 赵志刚, 刘昱, 刘永刚. 计及安全性与舒适性的智能车辆换道轨迹规划研究[J]. 交通运输系统工程与信息, 2024, 24(1): 55-65.
[2]	裴玉龙, 傅博涵, 王子奇, 张杰. 引力理论框架下基于综合竞争力的自动驾驶拟人换道决策模型[J]. 交通运输系统工程与信息, 2024, 24(1): 66-80.
[3]	李传耀, 张帆, 王涛, 黄德鑫, 唐铁桥. 基于深度强化学习的道路交叉口生态驾驶策略研究[J]. 交通运输系统工程与信息, 2024, 24(1): 81-92.
[4]	王丹, 林业. 警告刺激对驾驶员接管性能的影响机理研究[J]. 交通运输系统工程与信息, 2024, 24(1): 106-114.
[5]	李岩, 王泰州, 徐金华, 陈姜会, 汪帆. 面向动态交通分配的交通需求深度学习预测方法[J]. 交通运输系统工程与信息, 2024, 24(1): 115-123.
[6]	任其亮, 徐韬, 刘媛, 程龙春. 考虑载客状态的改进孤立森林浮动车异常数据检测算法[J]. 交通运输系统工程与信息, 2024, 24(1): 124-131.
[7]	袁见, 刘福强, 安琨, 郑喆, 马万经, 俞秋田. 基于交通波特征的车道级车流溯源方法[J]. 交通运输系统工程与信息, 2024, 24(1): 159-167.
[8]	曲大义, 孟奕名, 王韬, 宋慧, 陈意成. 基于分子力场的网联自主车辆跟驰安全特性及模型[J]. 交通运输系统工程与信息, 2023, 23(6): 33-41.
[9]	郭凤香, 黄金涛, 陈昱光, 郭延永, 刘攀. 多种缺失模式下交通数据组合近似填补方法[J]. 交通运输系统工程与信息, 2023, 23(6): 42-50.
[10]	蒋贤才, 徐慧智. 混合驾驶环境下交叉口空间资源动态控制方法[J]. 交通运输系统工程与信息, 2023, 23(6): 63-73.
[11]	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.
[12]	李泰国, 张天策, 李超, 周星宏. 基于面部倒立摆模型与信息熵的驾驶员疲劳检测[J]. 交通运输系统工程与信息, 2023, 23(5): 24-32.
[13]	蒋贤才, 程国柱. 网联交通环境下交叉口进口车道动态配置方法[J]. 交通运输系统工程与信息, 2023, 23(5): 55-66.
[14]	李鹏程, 董宝田, 李思贤. 基于时间图注意力的交叉口交通状态识别及关联度研究[J]. 交通运输系统工程与信息, 2023, 23(5): 67-74.
[15]	蔡浩, 李林峰, 李涵, 李新, 周腾. 基于极限学习机的短期交通流预测混合优化模型[J]. 交通运输系统工程与信息, 2023, 23(5): 75-82.

基于手机信令的城市机动化方式细分双层模型研究

Two-layer Model to Distinguish Urban Motorized Travel Mode Based on Mobile Phone Signaling Data

PDF

PDF(English version)

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