City Geospatial Dashboard: IoT and Big Data Analytics for Geospatial Solutions Provider in Disaster Management

被引:21
作者
Lwin, Ko Ko [1 ]
Sekimoto, Yoshihide [1 ]
Takeuchi, Wataru [2 ]
Zettsu, Koji [3 ]
机构
[1] Univ Tokyo, Inst Ind Sci, Human Ctr Urban Informat, Tokyo 1538505, Japan
[2] Univ Tokyo, Inst Ind Sci, Remote Sensing Environm & Disaster, Tokyo 1538505, Japan
[3] NICT Natl Inst Informat & Commun Technol, Big Data Analyt Lab, Tokyo, Japan
来源
2019 INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGIES FOR DISASTER MANAGEMENT (ICT-DM 2019) | 2019年
基金
日本科学技术振兴机构;
关键词
geospatial dashboard; IoT; big data analytics; geovisualisation; disaster management;
D O I
10.1109/ict-dm47966.2019.9032921
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Geospatial information generated from satellites, drones, and big data (mobile CDR (call details record), GPS trajectory data, wireless sensor network, and IoT (Internet of Things)) are important to all processes in disaster management such as disaster mitigation, preparedness, response, and mitigation. The emergence of a global navigation system and wireless communication technology changed the way we live and how we collect geospatial data in the field. For example, a large amount of geospatial data streams from the data repository as a base map in the field, and many IoT devices can collect and transmit geospatial data to IoT cloud server or centralised geodatabases. Moreover, collection, sharing and visualisation of all collected geospatial data is a crucial task for effective disaster planning and mitigation. Proper information needs to reach appropriate disaster management teams in minimal time to reduce loss of life and property. In this paper, we discuss establishment of a City Geospatial Dashboard, which can collect, share and visualise geospatial data collected from satellites, IoT devices, and other big data. We also explain geovisualisation of big data analytical results such as near-real-time rainfall profiler, hourly grid population, link population and flow direction estimated from mobile CDR, and hourly link speed computed from bus/taxi GPS trajectory data in order to improve spatial thinking and planning processes in disaster management by providing a set of spatial analysis tools known as geovisualisation.
引用
收藏
页数:4
相关论文
共 8 条
[1]  
Dameri RP, 2017, PROGR IS, P67, DOI 10.1007/978-3-319-45766-6_4
[2]  
Lwin K., 2015, 2 IEEE INT C SPAT DA
[3]  
Lwin K.K., 2011, Journal of Geographic Information System, P382, DOI [DOI 10.4236/JGIS.2011.34037, 10.4236/jgis.2011.34037]
[4]   Estimation of Hourly Link Population and Flow Directions from Mobile CDR [J].
Lwin, Ko Ko ;
Sekimoto, Yoshihide ;
Takeuchi, Wataru .
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION, 2018, 7 (11)
[5]   Space-time multiple regression model for grid-based population estimation in urban areas [J].
Lwin, Ko Ko ;
Sugiura, Komei ;
Zettsu, Koji .
INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE, 2016, 30 (08) :1579-1593
[6]  
Lwin Koko., 2014, JGIS Journal of Geographic Information System, V06, P99, DOI 10.4236/jgis.2014.62011
[7]  
Okamoto K, 2005, INT GEOSCI REMOTE SE, P3414
[8]  
Sjöbergh J, 2014, COMM COM INF SC, V421, P3