Using qualitative spatial logic for validating crowd-sourced geospatial data

Du, Heshan and Nguyen, Hai Hoang and Alechina, Natasha and Logan, Brian and Jackson, Mike and Goodwin, John (2015) Using qualitative spatial logic for validating crowd-sourced geospatial data. In: Innovative Applications of Artificial Intelligence (IAAI-15), 25-29 Jan 2015, Austin, Texas, USA.

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (671kB) | Preview

Abstract

We describe a tool, MatchMaps, that generates sameAs and partOf matches between spatial objects (such as shops, shopping centres, etc.) in crowd-sourced and authoritative geospatial datasets. MatchMaps uses reasoning in qualitative spatial logic, description logic and truth maintenance techniques, to produce a consistent set of matches. We report the results of an initial eval- uation of MatchMaps by experts from Ordnance Survey (Great Britain’s National Mapping Authority). In both the case studies considered, MatchMaps was able to correctly match spatial objects (high precision and recall) with minimal human intervention.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published in: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence and the Twenty-Seventh Innovative Applications of Artificial Intelligence Conference: 25-30 January 2015, Austin, Texas, USA. Palo Alto, Calif. : AAAI Press, 2015, ISBN: 9781577356981, pp. 3948-3953
Schools/Departments: University of Nottingham UK Campus > Faculty of Engineering
University of Nottingham UK Campus > Faculty of Science > School of Computer Science
Depositing User: Alechina, Natasha
Date Deposited: 18 Sep 2015 11:00
Last Modified: 13 Sep 2016 16:32
URI: http://eprints.nottingham.ac.uk/id/eprint/30166

Actions (Archive Staff Only)

Edit View Edit View