基于个体记忆效应和距离效应的出行目的地识别

doi:10.3785/j.issn.1008-973X.2024.04.006

浙江大学学报(工学版)

2024, Vol. 58

Issue (4): 708-717 DOI: 10.3785/j.issn.1008-973X.2024.04.006

计算机与控制工程

基于个体记忆效应和距离效应的出行目的地识别

郑思静1(

),陈勇2,朱奕璋1,陈喜群2,*(

)

1. 浙江大学工程师学院智能交通研究所，浙江杭州 310058
2. 浙江大学建筑工程学院智能交通研究所，浙江杭州 310058

Trip destination recognition based on individual memory effect and distance effect

Sijing ZHENG1(

),Yong CHEN2,Yizhang ZHU1,Xiqun CHEN2,*(

)

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

全文: PDF(2793 KB) HTML

摘要：

通过分析个体出行轨迹数据，挖掘个体出行历史记忆特征以及个体所处位置与潜在目的地的距离特征，建立新的出行目的地识别模型. 利用杭州市200个匿名个体62880次出行数据测试所建模型的效果. 对基于位置的服务（LBS）数据进行预处理，提取以活动为目的的分段出行数据片段，采用GeoHash网格编码方法得到网格化后的个体历史目的地集合. 利用随机缺失的个体出行历史轨迹数据构建训练集和测试集，采用非线性最小二乘法对模型进行参数标定. 结果表明，所建模型提升了出行目的地识别精度；对比不同模型的召回率、折扣累计收益和F1分数，所建模型优于马尔可夫模型、决策树模型以及随机森林模型；数据缺失率敏感性分析结果验证了所建模型的鲁棒性.

关键词： 智慧出行; 个体出行; 目的地识别; 记忆效应; 距离效应

Abstract:

A new travel destination recognition model was established through analyzing individual travel track data, mining the characteristics of individual travel history memory and the distance between individual location and potential destination. The model was tested using 62880 trips of 200 anonymous individuals in Hangzhou. The location based service (LBS) data was preprocessed, the segmented travel data fragments were extracted for the purpose of activity, and the meshed individual historical destination set was obtained by GeoHash grid coding method. The training set and test set were constructed by using the random missing individual travel history track data, and the parameters of the model were calibrated by nonlinear least square method. Results show that the proposed model improves the recognition accuracy of travel destination. Comparing the recall rate, discount cumulative return and F1 score of different models, the proposed model was better than the Markov model, decision tree model and random forest model. The robustness of the proposed model was verified by the sensitivity analysis of data missing rate.

Key words: smart mobility individual travel destination recognition memory effect distance effect

收稿日期: 2023-02-13 出版日期: 2024-03-27

CLC:

F 572

基金资助: 国家自然科学基金资助项目（72171210）；浙江省自然科学基金资助项目（LZ23E080002）.

通讯作者: 陈喜群 E-mail: sijingzheng@zju.edu.cn;chenxiqun@zju.edu.cn

作者简介: 郑思静（1998—），女，硕士生，从事交通大数据分析研究. orcid.org/0000-0003-2059-9586. E-mail：sijingzheng@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
	郑思静
	陈勇
	朱奕璋
	陈喜群

引用本文:

郑思静,陈勇,朱奕璋,陈喜群. 基于个体记忆效应和距离效应的出行目的地识别[J]. 浙江大学学报(工学版), 2024, 58(4): 708-717.

Sijing ZHENG,Yong CHEN,Yizhang ZHU,Xiqun CHEN. Trip destination recognition based on individual memory effect and distance effect. Journal of ZheJiang University (Engineering Science), 2024, 58(4): 708-717.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2024.04.006 或 https://www.zjujournals.com/eng/CN/Y2024/V58/I4/708

图 1 基于个体记忆效应和距离效应的出行目的地识别模型示意图

图 2 出行目的地识别模型流程图

图 3 个体出行次数降序排列

图 4 个体出行时间分布

图 5 个体出行目的地叠加分布

图 6 所有个体出行特征统计

图 7 真实与识别目的地分布对比

表 1 不同目的地识别模型性能对比

图 8 不同访问目的地个数的F1分数

表 2 个体记忆效应和距离效应模型的消融实验

图 9 所有个体出行特征对比

表 3 不同对比模型出行特征分布的JS散度

图 10 不同模型的出行散点图对比

图 11 不同模型的缺失率敏感性分析

图 12 所提模型的时间敏感性分析

1	ZHENG C, FAN X, WANG C, et al. GMAN: a graph multi-attention network for traffic prediction [C]// Proceedings of the AAAI Conference on Artificial Intelligence . [S.l.]: AAAI, 2020, 34: 1234–1241.
2	ZHAO P, LUO A, LIU Y, et al Where to go next: a spatio-temporal gated network for next POI recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 34 (5): 2512- 2524
3	QIAO Y, SI Z, ZHANG Y, et al A hybrid Markov-based model for human mobility prediction[J]. Neurocomputing, 2018, 278: 99- 109 doi: 10.1016/j.neucom.2017.05.101
4	YAN X Y, ZHAO C, FAN Y, et al Universal predictability of mobility patterns in cities[J]. Journal of The Royal Society Interface, 2014, 11 (100): 20140834
5	YAN X Y, WANG W X, GAO Z Y, et al Universal model of individual and population mobility on diverse spatial scales[J]. Nature Communications, 2017, 8: 1639 doi: 10.1038/s41467-017-01892-8
6	FENG J, LI Y, ZHANG C, et al. Deepmove: predicting human mobility with attentional recurrent networks [C]// Proceedings of the 2018 World Wide Web Conference . Loyn: [s.n.], 2018: 1459–1468.
7	桂志鹏, 杨乐, 丁劲宸, 等. 顾及路口转移偏好和当前移动模式的个体驾驶目的地预测方法[EB/OL]. (2022-03-29)[2024-01-10]. http://doi.org/10.13203/J.whugis20210555.
8	颜帅. 基于LBS数据的出行目的识别和轨迹预测研究[D]. 南京: 东南大学, 2020. YAN Shuai. A research on travel purpose recognition and trajectory prediction based on LBS data [D]. Nanjing: Southeast University , 2020.
9	ZHAO Y M, ZENG A, YAN X Y, et al Unified underpinning of human mobility in the real world and cyberspace[J]. New Journal of Physics, 2016, 18: 053025 doi: 10.1088/1367-2630/18/5/053025
10	SONG C, KOREN T, WANG P, et al Modelling the scaling properties of human mobility[J]. Nature Physics, 2010, 6: 818- 823 doi: 10.1038/nphys1760
11	GONZÁLEZ M C, HIDALGO C A, BARÁBASI A L Understanding individual human mobility patterns[J]. Nature, 2008, 453: 779- 782 doi: 10.1038/nature06958
12	ANDERSON J E The gravity model[J]. Annual Review of Economics, 2011, 3 (1): 133- 160 doi: 10.1146/annurev-economics-111809-125114
13	周艺华, 李广辉, 杨宇光, 等基于GeoHash的近邻查询位置隐私保护方法[J]. 计算机科学, 2019, 46 (8): 212- 216 ZHOU Yihua, LI Guanghui, YANG Yuguang, et al Location privacy preserving nearest neighbor querying based on GeoHash[J]. Computer Science, 2019, 46 (8): 212- 216
14	洪文兴, 陈明韬, 刘伊灵, 等基于GeoHash和HDBSCAN的共享单车停车拥挤区域识别[J]. 厦门大学学报:自然科学版, 2022, 61 (6): 1030- 1037 HONG Wenxing, CHEN Mingtao, LIU Yiling, et al Identification of crowded parking areas for shared bikes based on GeoHash and HDBSCAN[J]. Journal of Xiamen University: Natural Science, 2022, 61 (6): 1030- 1037
15	JIANG F, LU Z N, GAO M, et al DP-BPR: destination prediction based on Bayesian personalized ranking[J]. Journal of Central South University, 2021, 28: 494- 506 doi: 10.1007/s11771-021-4617-x
16	ALESSANDRETTI L, SAPIEZYNSKI P, SEKARA V, et al Evidence for a conserved quantity in human mobility[J]. Nature Human Behaviour, 2018, 2: 485- 491 doi: 10.1038/s41562-018-0364-x
17	MATHEW W, RAPOSO R, MARTINS B. Predicting future locations with hidden Markov models [C]// Proceedings of the 2012 ACM Conference on Ubiquitous Computing . [S.l.]: ACM, 2012, 911–918.
18	KIM T, YUE Y, TAYLOR S, et al. A decision tree framework for spatiotemporal sequence prediction [C]// Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . [S.l.]: ACM, 2015: 577–586.
19	ZHOU Y, YANG C, ZHU R Identifying trip ends from raw GPS data with a hybrid spatio-temporal clustering algorithm and random forest model: a case study in Shanghai[J]. Transportation Planning and Technology, 2019, 42 (8): 739- 756 doi: 10.1080/03081060.2019.1675309
20	DUPRET G, PIWOWARSKI B Model based comparison of discounted cumulative gain and average precision[J]. Journal of Discrete Algorithms, 2013, 18: 49- 62 doi: 10.1016/j.jda.2012.10.002
21	熊亚军, 谢林柏, 彭力基于JS散度和潜在特征提取的多块PCA故障监测[J]. 仪表技术与传感器, 2022, (5): 105- 110 XIONG Yajun, XIE Linbo, PENG Li Multiblock PCA fault monitoring based on JS divergence and latent feature extraction[J]. Instrument Technique and Sensor, 2022, (5): 105- 110

[1]	吕福在,胡宇天,伍建军,王林翔. 双程形状记忆效应的唯象动力学模型[J]. 浙江大学学报(工学版), 2020, 54(4): 642-649.

Viewed

Full text

Abstract

Cited

Shared

Discussed