Metagraph-Based Life Pattern Clustering With Big Human Mobility Data

被引:7
作者
Li, Wenjing [1 ]
Zhang, Haoran [1 ,2 ]
Chen, Jinyu [1 ]
Li, Peiran [1 ]
Yao, Yuhao [1 ]
Shi, Xiaodan [1 ]
Shibasaki, Mariko [1 ]
Kobayashi, Hill Hiroki [1 ]
Song, Xuan [1 ,3 ]
Shibasaki, Ryosuke [1 ]
机构
[1] Univ Tokyo, Ctr Spatial Informat Sci, Kashiwa, Chiba 2778568, Japan
[2] Locat Mind Inc, Chiyoda Ku, Tokyo 1010032, Japan
[3] Southern Univ Sci & Technol, Southern Univ Sci & Technol Univ Tokyo Joint Res C, Dept Comp & Engn, Shenzhen 518055, Guangdong, Peoples R China
基金
日本学术振兴会;
关键词
Pattern clustering; Global Positioning System; Big Data; Measurement; Data structures; Time-frequency analysis; Semantics; Metagraph; life pattern clustering; big data; human mobility;
D O I
10.1109/TBDATA.2022.3155752
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Life pattern clustering is essential for abstracting the groups' characteristics of daily life patterns and activity regularity. Based on millions of GPS records, this research proposes a framework on the life pattern clustering which can efficiently identify the groups that have similar life patterns. The proposed method can retain original features of individual life pattern data without aggregation. Metagraph-based data structure is proposed for presenting the diverse life pattern. Spatial-temporal similarity includes significant places semantics, time-sequential properties and frequency are integrated into this data structure, which captures the uncertainty of an individual and the diversities between individuals. Non-negative-factorization-based method is utilized for reducing the dimension. The results show that our proposed method can effectively identify the groups that have similar life pattern in long term and takes advantage in computation efficiency and representational capacity compared with the traditional methods. We reveal the representative life pattern groups and analyze the group characteristics of human life patterns during different periods and different regions. We believe our work helps in future infrastructure planning, services improvement and policy making related to urban and transportation, thus promoting a humanized and sustainable city.
引用
收藏
页码:227 / 240
页数:14
相关论文
共 52 条
  • [1] Spatial structure, intra-urban commuting patterns and travel mode choice: Analyses of relationships in the Kumasi Metropolis, Ghana
    Acheampong, Ransford A.
    [J]. CITIES, 2020, 96
  • [2] [Anonymous], 2010, P 19 INT C WORLD WID, DOI [10.1145/1772690.1772795, DOI 10.1145/1772690.1772795]
  • [3] Mining urban sustainable performance: GPS data-based spatio-temporal analysis on on-road braking emission
    Chen, Jinyu
    Li, Wenjing
    Zhang, Haoran
    Jiang, Wenxiao
    Li, Weifeng
    Sui, Yi
    Song, Xuan
    Shibasaki, Ryosuke
    [J]. JOURNAL OF CLEANER PRODUCTION, 2020, 270
  • [4] Chen XP, 2016, AER ADV ENG RES, V69, P181
  • [5] Mining human mobility patterns from social geo-tagged data
    Comito, Carmela
    Falcone, Deborah
    Talia, Domenico
    [J]. PERVASIVE AND MOBILE COMPUTING, 2016, 33 : 91 - 107
  • [6] Detection of Activities of Public Transport Users by Analyzing Smart Card Data
    Devillaine, Flavio
    Munizaga, Marcela
    Trepanier, Martin
    [J]. TRANSPORTATION RESEARCH RECORD, 2012, (2276) : 48 - 55
  • [7] Donoho D, 2004, ADV NEUR IN, V16, P1141
  • [8] ElMahrsi M. K., 2014, PROC ACM SIGKDD WORK
  • [9] Fengli Xu, 2018, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, V2, DOI 10.1145/3191778
  • [10] Identifying spatiotemporal urban activities through linguistic signatures
    Fu, Cheng
    McKenzie, Grant
    Frias-Martinez, Vanessa
    Stewart, Kathleen
    [J]. COMPUTERS ENVIRONMENT AND URBAN SYSTEMS, 2018, 72 : 25 - 37