Geospatial Web Mining for Emergency Management

Fritz, Christian ; Kirschner, Christian ; Reker, Daniel ; Wisplinghoff, Andre ; Paulheim, Heiko ; Probst, Florian

paper.pdf - Published

Download (487kB)

Additional URL:
URN: urn:nbn:de:bsz:180-madoc-330567
Document Type: Conference presentation
Year of publication: 2010
Conference title: GIScience 2010: Sixth International Conference on Geographic Information Science
Location of the conference venue: Zurich, Switzerland
Date of the conference: 14.-17.9.2010
Publication language: English
Institution: School of Business Informatics and Mathematics > Information Systems V: Web-based Systems (Bizer 2012-)
Subject: 004 Computer science, internet
Abstract: Emergency management is a domain where information has to be gathered, aggrega ted, and visualized dynamically and quickly. By providing the right information at the right time, the chaos phase between the occurrence of a disaster and the start of well - organized relief measures can be significantly shortened (Paulheim et al. 2009). T he information needed in an emergency scenario can be quite diverse. For example, a person planning an evacuation may need to know about companies that can transport people, and places that can serve as emergency shelters. For the first, bus and taxi compa nies, logistics companies as well as rental car providers may be taken into account. The latter may include hotels and schools as well as sports arenas and concert venues. Although all this information is available on the web, it cannot be easily accessed. Since such non - trivial categories such as buildings that can serve as emergency shelter are not sharply defined, one cannot simply enter emergency shelter into Google and retrieve a list of emergency shelters. Instead, lots of subsequent manual searches h ave to be performed, and the results have to be aggregated by hand. Visual exploration is even more difficult. While several emergency management tools exist (cf. (Paulheim et al. 2009) for a survey), this concern has not been addressed in this context yet. In this paper, we introduce a prototype which allows for a - priori crawling the web for relevant information on objects belonging to non - trivial categories and provide the aggregated results as an OGC compliant web feature service for visual exploration.

Dieser Eintrag ist Teil der Universitätsbibliographie.

Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.

Metadata export


+ Search Authors in

+ Download Statistics

Downloads per month over past year

View more statistics

You have found an error? Please let us know about your desired correction here: E-Mail

Actions (login required)

Show item Show item