基于时空数据的驻留行为特征可视分析

doi:10.19678/j.issn.1000-3428.0064093

摘要/Abstract

摘要： 随着智慧城市的快速发展，大量商业场所每天会产生海量的驻留行为数据，然而传统驻留行为数据分析方法难以克服数据稀疏性问题，并且对于时空伴随关系的发现准确度也较低。根据驻留行为数据特征和可视分析任务，设计一种交互式的可视分析系统。对原始数据进行处理，提取相关的时空特征并发现用户伴随关系。使用改进的可变滑动窗口算法，并结合可视分析技术，设计用户关系图、时间甘特图、多变量表达的示意性地图、径向条形图、日历热力图等多种视图，实现对驻留场所的流量分布、用户来源等特征的多时段可视分析。应用两个真实数据集进行案例分析，并对发现的行为模式及对应现象进行解释说明，证明了该系统的可用性和拓展性，并表明其可实现团体出行特征和场所流量分析等系统级应用，为相关经营性商业场所提供合理化建议及辅助决策支持。

关键词: 可视分析, 时空数据, 驻留行为数据, 时空伴随关系, 多变量表达

Abstract: Owing to the rapid development of smart cities, a significant number of commercial areas will generate plenty of resident behavior data daily.However, classical analysis methods cannot easily overcome data sparsity, and spatio-temporal adjoint relation discovery does not provide accurate results.This paper proposes an interactive visual analysis system based on resident behavior data characteristics and visual analysis tasks.The system processes the original data, extracts the relevant spatio-temporal characteristics, and identifies the user's adjoint relations.Additionally, the system uses an improved variable sliding window algorithm combined with visual analysis technology to design a user relationship diagram, time Gantt chart, schematic map of multivariable representation, radial bar chart, calendar thermal chart, and others.Based on these visual tools, the traffic distribution, user origin, and other characteristics of the residence site can be visually analyzed in multiple periods.By performing case studies based on two real datasets, the behavior patterns and phenomena that prove the usability and extensibility of the proposed system are explained.Results show that the visual analysis system can realize system-level applications such as group travel characteristics and traffic analysis, which can provide reasonable suggestions and assist decision-making for the commercial operation of relevant venues.

Key words: visual analysis, spatio-temporal data, resident behavior data, spatio-temporal adjoint relation, multivariable representation

中图分类号:

TP391

马小东, 赵凡, 任芃锟. 基于时空数据的驻留行为特征可视分析[J]. 计算机工程, 2023, 49(2): 105-111.

MA Xiaodong, ZHAO Fan, REN Pengkun. Visual Analysis of Resident Behavior Characteristics Based on Spatio-Temporal Data[J]. Computer Engineering, 2023, 49(2): 105-111.

http://www.ecice06.com/CN/Y2023/V49/I2/105

图/表 6

20230216180643

20230216180646

20230216180649

20230216180653

20230216180656

20230216180659

参考文献

[1] GUO X G, XU Z J, ZHANG J Q, et al.An OD flow clustering method based on vector constraints:a case study for Beijing taxi origin-destination data[J].ISPRS International Journal of Geo-Information, 2020, 9(2):128.
[2] 赵凡, 蒋同海, 周喜, 等.面向多维稀疏时空数据的可视化研究[J].中国科学技术大学学报, 2017, 47(7):556-568. ZHAO F, JIANG T H, ZHOU X, et al.Visualization of multi-dimensional sparse spatial-temporal data[J].Journal of University of Science and Technology of China, 2017, 47(7):556-568.(in Chinese)
[3] 王慧东, 宋耀莲, 田榆杰.一种多属性的时空数据聚类算法分析研究[J].重庆邮电大学学报(自然科学版), 2021, 33(4):661-668. WANG H D, SONG Y L, TIAN Y J.Research on a multi-attribute spatial-temporal data clustering algorithm[J].Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition), 2021, 33(4):661-668.(in Chinese)
[4] 涂伟, 曹劲舟, 高琦丽, 等.融合多源时空大数据感知城市动态[J].武汉大学学报(信息科学版), 2020, 45(12):1875-1883. TU W, CAO J Z, GAO Q L, et al.Sensing urban dynamics by fusing multi-sourced spatiotemporal big data[J].Geomatics and Information Science of Wuhan University, 2020, 45(12):1875-1883.(in Chinese)
[5] MASAHIKO I, YOKOYAMA D, TOYODA M, et al.Visual exploration of changes in passenger flows and tweets on mega-city metro network[J].IEEE Transactions on Big Data, 2016, 2(1):85-99.
[6] 包恒彬, 马玉鹏, 杨奉毅, 等.基于时空注意力机制的加油站级客流量预测[J].计算机工程, 2021, 47(4):291-297. BAO H B, MA Y P, YANG F Y, et al.Gas station-level foot traffic prediction based on spatial-temporal attention mechanism[J].Computer Engineering, 2021, 47(4):291-297.(in Chinese)
[7] ZHANG J B, ZHENG Y, QI D K.Deep spatio-temporal residual networks for citywide crowd flows prediction[EB/OL].[2022-02-04].https://arxiv.org/abs/1610.00081v1.
[8] LIU Y, ESTER M, QIAN Y Q, et al.Microscopic and macroscopic spatio-temporal topic models for check-in data[J].IEEE Transactions on Knowledge and Data Engineering, 2017, 29(9):1957-1970.
[9] LEEMANS M, VAN DER AALST W M P.Recursion aware modeling and discovery for hierarchical software event log analysis[C]//Proceedings of the 25th International Conference on Software Analysis, Evolution and Reengineering.Washington D.C., USA:IEEE Press, 2018:185-196.
[10] LI J, CHEN S M, ANDRIENKO G, et al.Visual exploration of spatial and temporal variations of tweet topic popularity[C]//Proceedings of 2018 EuroVis Workshop on Visual Analytics.Bron, France:[s.n.], 2018:7-11.
[11] PENG X F, PAN Y M, LUO J B.Predicting high taxi demand regions using social media check-ins[C]//Proceedings of IEEE International Conference on Big Data.Washington D.C., USA:IEEE Press, 2017:2066-2075.
[12] CHEN Y Y, ZHANG J Y, GUO M Y, et al.Understanding customer behaviour in urban shopping mall from WiFi logs[C]//Proceedings of IEEE International Conference on Pervasive Computing and Communications Workshops.Washington D.C., USA:IEEE Press, 2017:50-53.
[13] FRHAN A J.Visualization and analysis of user behaviour patterns for multimedia content view in social networks[C]//Proceedings of the 5th International Symposium on Electrical and Electronics Engineering.Washington D.C., USA:IEEE Press, 2017:1-7.
[14] 李丛敏, 李杰, 张康, 等.面向签到日志的用户行为模式交互探索[J].软件学报, 2019, 30(6):1819-1834. LI C M, LI J, ZHANG K, et al.Interactive exploration of behavior patterns from check-in logs[J].Journal of Software, 2019, 30(6):1819-1834.(in Chinese)
[15] HE C B, FEI X, LI H C, et al.Community discovery in large-scale complex networks using distributed SimRank nonnegative matrix factorization[C]//Proceedings of the 5th International Conference on Advanced Cloud and Big Data.Washington D.C., USA:IEEE Press, 2017:226-231.
[16] DOI C, KATAGIRI M, ISHII A, et al.Estimating customer preference through store check-in histories and its use in visitor promotion[C]//Proceedings of the 10th International Conference on Mobile Computing and Ubiquitous Network.Washington D.C., USA:IEEE Press, 2017:1-6.
[17] 王齐童, 王鹏, 赵郁亮, 等.一种高效的移动对象伴随模式挖掘算法[J].计算机工程, 2020, 46(4):97-106, 122. WANG Q T, WANG P, ZHAO Y L, et al.An efficient adjoint pattern mining algorithm for moving object[J].Computer Engineering, 2020, 46(4):97-106, 122.(in Chinese)
[18] LIU D Y, WENG D, LI Y H, et al.SmartAdP:visual analytics of large-scale taxi trajectories for selecting billboard locations[J].IEEE Transactions on Visualization and Computer Graphics, 2017, 23(1):1-10.
[19] KRUEGER R, HEIMERL F, HAN Q, et al.Visual analysis of visitor behavior for indoor event management[C]//Proceedings of the 48th Hawaii International Conference on System Sciences.Washington D.C., USA:IEEE Press, 2015:1148-1157.
[20] LI D C, WANG Y J, WU S, et al.An visual analytics approach to explore criminal patterns based on multidimensional data[C]//Proceedings of IEEE International Geoscience and Remote Sensing Symposium.Washington D.C., USA:IEEE Press, 2017:5563-5566.
[21] ZHAO Y, SHE Y M, CHEN W J, et al.EOD edge sampling for visualizing dynamic network via massive sequence view[J].IEEE Access, 2018, 6:53006-53018.
[22] ZHANG X, WANG Q Y.PeopleVis:a visual analysis system for mining travel behavior[C]//Proceedings of the 21st International Conference on Computer Supported Cooperative Work in Design.Washington D.C., USA:IEEE Press, 2017:463-468.
[23] LI J, CHEN S, CHEN W, et al.Semantics-space-time cube:a conceptual framework for systematic analysis of texts in space and time[J].IEEE Transactions on Visualization and Computer Graphics, 2020, 26(4):1789-1806.
[24] ZHOU D B, LI H, LIU S, et al.A map-based visual analysis method for patterns discovery of mobile learning in education with big data[C]//Proceedings of IEEE International Conference on Big Data.Washington D.C., USA:IEEE Press, 2018:3482-3491.
[25] ZHAO Y, LUO F, CHEN M H, et al.Evaluating multi-dimensional visualizations for understanding fuzzy clusters[J].IEEE Transactions on Visualization and Computer Graphics, 2019, 25(1):12-21.

选择文件类型/文献管理软件名称

选择包含的内容