Mining and correlating traffic events from human sensor observations with official transport data using self-organizing-maps

被引:22
作者
Steiger, Enrico [1 ]
Resch, Bernd [2 ,3 ]
de Albuquerque, Joao Porto [4 ]
Zipf, Alexander [1 ]
机构
[1] Heidelberg Univ, Inst Geog, GISci Res Grp, Heidelberg, Germany
[2] Salzburg Univ, Dept Geoinformat, Z GIS, Salzburg, Austria
[3] Harvard Univ, Ctr Geog Anal, Cambridge, MA 02138 USA
[4] Univ Warwick, Ctr Interdisciplinary Methodol, Warwick, England
关键词
Traffic data; Twitter; Self-organizing map; Point pattern analysis; Human mobility; GEO-SOM; PATTERNS; TWITTER;
D O I
10.1016/j.trc.2016.10.010
中图分类号
U [交通运输];
学科分类号
08 ; 0823 ;
摘要
Cities are complex systems, where related Human activities are increasingly difficult to explore within. In order to understand urban processes and to gain deeper knowledge about cities, the potential of location-based social networks like Twitter could be used a promising example to explore latent relationships of underlying mobility patterns. In this paper, we therefore present an approach using a geographic self-organizing map (Geo-SOM) to uncover and compare previously unseen patterns from social media and authoritative data. The results, which we validated with Live Traffic Disruption (TIMS) feeds from Transport for London, show that the observed geospatial and temporal patterns between special events (r = 0.73), traffic incidents (r = 0.59) and hazard disruptions (r = 0.41) from TIMS, are strongly correlated with traffic-related, georeferenced tweets. Hence, we conclude that tweets can be used as a proxy indicator to detect collective mobility events and may help to provide stakeholders and decision makers with complementary information on complex mobility processes. (C) 2016 Elsevier Ltd. All rights reserved.
引用
收藏
页码:91 / 104
页数:14
相关论文
共 53 条
  • [11] Batch kernel SOM and related Laplacian methods for social network analysis
    Boulet, Romain
    Jouve, Bertrand
    Rossi, Fabrice
    Villa, Nathalie
    [J]. NEUROCOMPUTING, 2008, 71 (7-9) : 1257 - 1273
  • [12] Couronne T, 2013, ARXIV13016574
  • [13] Cranshaw J, 2012, P ICWSM DUBL IR
  • [14] Combining Geo-SOM and Hierarchical Clustering to Explore Geospatial Data
    Feng, Chen-Chieh
    Wang, Yi-Chen
    Chen, Chih-Yuan
    [J]. TRANSACTIONS IN GIS, 2014, 18 (01) : 125 - 146
  • [15] THE MODIFIABLE AREAL UNIT PROBLEM IN MULTIVARIATE STATISTICAL-ANALYSIS
    FOTHERINGHAM, AS
    WONG, DWS
    [J]. ENVIRONMENT AND PLANNING A, 1991, 23 (07) : 1025 - 1044
  • [16] Spatio-Temporal Analytics for Exploring Human Mobility Patterns and Urban Dynamics in the Mobile Age
    Gao, Song
    [J]. SPATIAL COGNITION AND COMPUTATION, 2015, 15 (02) : 86 - 114
  • [17] Understanding individual human mobility patterns
    Gonzalez, Marta C.
    Hidalgo, Cesar A.
    Barabasi, Albert-Laszlo
    [J]. NATURE, 2008, 453 (7196) : 779 - 782
  • [18] Citizens as sensors: the world of volunteered geography
    Goodchild, Michael
    [J]. GEOJOURNAL, 2007, 69 (04) : 211 - 221
  • [19] Gorricha J., 2013, INT J ADV INTELL SYS, V6
  • [20] Hagenauer J., 2010, P 25 C INT CART ASS