吉林大学学报(工学版) ›› 2026, Vol. 56 ›› Issue (3): 725-733.doi: 10.13229/j.cnki.jdxbgxb.20240887

• 交通运输工程·土木工程 • 上一篇    

基于CFSFDP-BP的车辆出行群体分类及识别方法

谢坤1(),董宏辉1,卢玲玉2,耿庆桥3,李鹏辉1(),董春娇1   

  1. 1.北京交通大学 综合交通运输大数据应用技术交通运输行业重点实验室，北京 100044
    2.中国城市规划设计研究院深圳分院 市政所，广东 深圳 518040
    3.交通运输部规划研究院 公路所，北京 100028
  • 收稿日期:2024-08-08 出版日期:2026-03-01 发布日期:2026-03-31
  • 通讯作者: 李鹏辉 E-mail:xiekun@bjtu.edu.cn;9323@bjtu.edu.cn
  • 作者简介:谢坤（1982-），男，博士研究生.研究方向：交通安全，低碳交通. E-mail： xiekun@bjtu.edu.cn
  • 基金资助:
    国家重点研发计划项目(2023YFC3009601);2023年度国家社科基金重大项目(23&ZD138)

Classification and recognition method of vehicle travel groups based on CFSFDP-BP

Kun XIE1(),Hong-hui DONG1,Ling-yu LU2,Qing-qiao GENG3,Peng-hui LI1(),Chun-jiao DONG1   

  1. 1.Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport，Ministry of Transport，Beijing Jiaotong University，Beijing 100044，China
    2.Municipal Engineering Department，China Academy of Urban Planning & Design Shenzhen Branch，Shenzhen 518040，China
    3.Institute of Highways，Planning and Research Institute of the Ministry of Transport，Beijing 100028，China
  • Received:2024-08-08 Online:2026-03-01 Published:2026-03-31
  • Contact: Peng-hui LI E-mail:xiekun@bjtu.edu.cn;9323@bjtu.edu.cn

RICH HTML

 1   

PDF (PC)

23

摘要：

以货车和私家车出行轨迹数据为基础，以出行开始时间、出行结束时间、总运行时长等7个出行指标作为特征量，提出了基于密度峰值聚类的（CFSFDP）出行群体分类方法，将货车和私家车分别划分为三类出行群体。以出行特征指标为输入，密度聚类算法的分类标签为输出，建立基于BP网络的车辆出行群体类别识别模型，实现对同一车型下的不同出行群体的快速识别。研究结果表明：提出的基于CFSFDP-BP的车辆出行群体分类及识别方法预测精度和可靠性较好，对货车出行群体类别的识别准确率为0.991，对私家车出行群体类别识别准确率为0.988，且对货车出行群体的识别效果优于私家车的识别效果。货车出行群体可划分为灵活型-低强度、传统型-中强度以及传统型-高强度三类；私家车出行群体可划分为通勤型-低强度、通勤型-中强度以及灵活型-高强度三类出行特征群体。研究结果能够为交管部门制定精细化的交通管理策略，提高交通运行效率提供支持。

关键词: 道路交通, 货车与私家车, 出行特征, 密度峰值聚类算法, 出行群体识别

Abstract:

Based on truck and private car trajectory data， a trip group classification method using Clustering by fast search and find of density peaks（CFSFDP） was proposed， in which seven trip indicators—including trip start time， trip end time， and total operation duration—were employed as feature variables. The trucks and private cars were respectively divided into three trip groups. A BP neural network-based vehicle trip group identification model was subsequently established， with trip characteristic indicators serving as inputs and the density clustering algorithm's classification labels as outputs， thereby enabling rapid identification of different trip groups within the same vehicle type.The results indicated that the proposed CFSFDP-BP-based trip group classification and identification method demonstrated satisfactory prediction accuracy and reliability. An identification accuracy of 0.991 was achieved for truck trip groups， while 0.988 was obtained for private car trip groups， with superior performance observed for truck trip group identification compared to private cars. Three distinct truck trip groups were identified： flexible-low intensity， traditional-medium intensity， and traditional-high intensity. Meanwhile， three private car trip groups were classified as commute-low intensity， commute-medium intensity， and flexible-high intensity. These findings are expected to support traffic management authorities in formulating refined traffic management strategies and improving traffic operational efficiency.

Key words: road traffic, trucks and private cars, travel characteristics, clustering by fast search and find of density peaks, identification of travel groups

中图分类号: 

  • U491.1

图1

聚类结果及车辆占比"

表1

货车群体识别模型评估结果"

车型数据集准确率召回率精确率F1
货车训练集0.9890.9890.9890.989
测试集0.9910.9910.9910.991
私家车训练集0.9900.9900.9900.990
测试集0.9880.9880.9880.988

图2

出行开始与结束时段分布特征"

图3

总运行时长与平均停留时间"

图4

平均出行时间与出行次数"

[1] Zhou T, Zhang J. Analysis of commercial truck drivers' potentially dangerous driving behaviors based on 11-month digital tachograph data and multilevel modeling approach[J]. Accident Analysis & Prevention, 2019, 132: No.105256.
[2] Du J, Aultman-hall L. Increasing the accuracy of trip rate information from passive multi-day GPS travel datasets: automatic trip end identification issues[J]. Transportation Research Part A: Policy and Practice, 2007, 41(3): 220-232.
[3] 周荣贵, 高沛, 李雨璇, 等. 基于轨迹数据的高速公路小客车异常驾驶行为阈值[J]. 吉林大学学报:工学版,2024,54(9):2581-2587.
Zhou Rong-gui, Gao Pei, Li Yu-xuan, et al. Abnormal driving behavior thresholds of highway minibuses based on trajectory data[J]. Journal of Jilin University(Engineering and Technology Edition),2024,54(9):2581-2587.
[4] 张健钦, 仇培元, 杜明义. 基于时空轨迹数据的出行特征挖掘方法[J]. 交通运输系统工程与信息, 2014, 14(6): 72-78.
Zhang Jian-qin, Qiu Pei-yuan, Du Ming-yi. Mining method of travel characteristics based on spatio-temporal trajectory data[J]. Journal of Transportation Syatem Engineering and Information Technology, 2014, 14(6): 72-78.
[5] 张文畅. 基于轨迹数据的货车司机货运特征画像及应用研究[D]. 成都:西南交通大学交通运输与物流学院, 2021.
Zhang Wen-chang. Research on the characteristic portrait of truck drivers based on trajectory data[D]. Chengdu: School of Transportation and Logistics,Southwest Jiaotong University, 2021.
[6] 薛倩, 李旭, 王建春. 基于GPS数据的青岛市货运车辆出行特征分析[J]. 中阿科技论坛, 2023(5): 96-100.
Xue Qian, Li Xu, Wang Jian-chun. Research on the travel characteristics of freight vehicles in Qingdao based on GPS data[J]. China-Arab States Science and Technology Forum, 2023(5): 96-100.
[7] 王静. 基于GPS数据的货运车辆出行特性研究[D]. 北京:北京交通大学交通运输学院, 2022.
Wang Jing. Research on travel characteristics of freight vehicles based on GPS data[D]. Beijing: School of Traffic and Transportation, Beijing Jiaotong University, 2022.
[8] Gan M, Nie Y M, Liu X, et al. Whereabouts of truckers: an empirical study of predictability[J]. Transportation Research Part C: Emerging Technologies, 2019, 104: 184-195.
[9] 魏广奇, 苏跃江, 吴德馨, 等. 基于高速公路流水数据的通勤车辆特征研究[J]. 交通运输系统工程与信息, 2019, 19(3): 237-244.
Wei Guang-qi, Su Yue-jiang, Wu De-xin, et al. Trip characteristics of vehicle with commuting property based on highway ticket data[J]. Journal of Transportation Systems Engineering and Information Technology, 2019, 19(3): 237-244.
[10] 杨帅, 刘樟伟, 杨宇星, 等. 基于高快速路卡口数据的车辆出行特征分析[C]∥中国城市交通规划年会, 青岛, 2018:No.13.
Yang Shuai, Liu Zhang-wei, Yang Yu-xing, et al. Analysis of vehicle travel characteristics based on tollgate data of highways and expressways[C]∥Annual Conference of Urban Transport Planning in China, Qingdao, China,2018:No.13.
[11] Zhou K, Tian Z, Yang Y. Periodic pattern detection algorithms for personal trajectory data based on spatiotemporal multi-granularity[J]. IEEE Access, 2019,7: 99683-99693.
[12] Zhao J, Qu Q, Zhang F, et al. Spatio-temporal analysis of passenger travel patterns in massive smart card data[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(11): 3135-3146.
[13] Zhang S, Tang J, Wang H, et al. Revealing intra-urban travel patterns and service ranges from taxi trajectories[J]. Journal of Transport Geography, 2017, 61: 72-86.
[14] 汪涛. 基于历史行车轨迹集的车辆出行模式可视分析方法研究[D]. 合肥:合肥工业大学计算机与信息学院, 2021.
Wang Tao. Research on visual analysis method of vehicle travel pattern based on historical driving track set[D]. Hefei: School of Computer and Information, Hefei University of Technology, 2021.
[15] 黄正国. 基于车牌识别数据的车辆出行特征研究[D]. 成都:西南交通大学交通运输与物流学院, 2019.
Huang Zheng-guo. Research on vehicle travel feature based on license plate recognition data[D]. Chengdu: School of Transportation and Logistics, Southwest Jiaotong University, 2019.
[16] 梁泉, 翁剑成, 林鹏飞, 等. 基于个体出行图谱的公共交通通勤行为辨别方法研究[J]. 交通运输系统工程与信息, 2018, 18(2): 100-107.
Liang Quan, Weng Jian-cheng, Lin Peng-fei, et al. Public transport commuter identification based on individual travel graph[J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(2): 100-107.
[17] 马晓磊, 姚李亮, 沈宣良. 基于OBD数据的驾驶人出行模式挖掘[J]. 交通信息与安全, 2021, 39(2): 70-77.
Ma Xiao-lei, Yao Li-liang, Shen Xuan-liang. Drivers' travel pattern mining based on OBD data[J]. Journal of Transport Information and Safety, 2021, 39(2): 70-77.
[18] Alex Rodriguez, Alessandro Laio. Clustering by fast search and find of density peaks[J]. Science, 2014, 344(6191): 1492-1496.
[1] 马书红,张俊杰,陈西芳,廖国美. 利用出租车时序数据识别城市功能区[J]. 吉林大学学报(工学版), 2025, 55(2): 603-613.
[2] 黄晓明,赵润民. 道路交通基础设施韧性研究现状及展望[J]. 吉林大学学报(工学版), 2023, 53(6): 1529-1549.
[3] 潘恒彦,张文会,梁婷婷,彭志鹏,高维,王永岗. 基于MIMIC与机器学习的出租车驾驶员交通事故诱因分析[J]. 吉林大学学报(工学版), 2023, 53(2): 457-467.
[4] 马社强,邵春福,刘东,王军利,马壮林. 基于差异驱动原理的道路交通安全评价[J]. 吉林大学学报(工学版), 2010, 40(04): 981-0985.
[5] 刘研,高青,黄勇,于鸣,张忠进. 地能利用中道路融雪逐年运行过程分析[J]. 吉林大学学报(工学版), 2010, 40(01): 72-0076.
[6] 秦进,史峰,邓连波,肖龙文. 道路交通网络效率定量评价方法及其应用[J]. 吉林大学学报(工学版), 2010, 40(01): 47-0051.
[7] 王殿海，孙锋，金盛 . 两相位交叉口左转车通行能力计算方法[J]. 吉林大学学报(工学版), 2007, 37(04): 767-771.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 《吉林大学学报(工学版)》编辑部
地址：长春市人民大街5988号　电话：+86-431-85095297　传真：+86-431-85094074　E-mail: xbgxb@jlu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发