Bischof, Stefan, Martin, Christoph, Polleres, Axel, Schneider, Patrik. 2015. Collecting, Integrating, Enriching and Republishing Open City Data as Linked Data. In Proceedings of the 14th International Semantic Web Conference, Hrsg. Marcelo Arenas, Oscar Corcho, Elena Simperl, Markus Strohmaier, Mathieu d'Aquin, Kavitha Srinivas, Paul T. Groth, Michel Dumontier, Jeff Heflin, Krishnaprasad Thirunarayan, Steffen Staab, 57-75. Bethlehem, PA: Springer.

RIS

@INPROCEEDINGS{Bischof2015,
title = {Collecting, Integrating, Enriching and Republishing Open City Data as Linked Data},
author = {Stefan Bischof and Christoph Martin and Axel Polleres and Patrik Schneider},
publisher = {Springer},
year = {2015},
isbn = {978-3-319-25009-0},
address = {Bethlehem, PA},
url = {http://dx.doi.org/10.1007/978-3-319-25010-6},
publisher = {Springer},
volume = {9367},
language = {EN},
pages = {57-75},
series = {Proceedings of the 14th International Semantic Web Conference},
abstract = {Access to high quality and recent data is crucial both for decision makers in cities as well as for the public. Likewise, infrastructure providers could offer more tailored solutions to cities based on such data. However, even though there are many data sets containing relevant indicators about cities available as open data, it is cumbersome to integrate and analyze them, since the collection is still a manual process and the sources are not connected to each other upfront. Further, disjoint indicators and cities across the available data sources lead to a large proportion of missing values when integrating these sources. In this paper we present a platform for collecting, integrating, and enriching open data about cities in a reusable and comparable manner: we have integrated various open data sources and present approaches for predicting missing values, where we use standard regression methods in combination with principal component analysis (PCA) to improve quality and amount of predicted values. Since indicators and cities only have partial overlaps across data sets, we particularly focus on predicting indicator values across data sets, where we extend, adapt, and evaluate our prediction model for this particular purpose: as a "side product" we learn ontology mappings (simple equations and sub-properties) for pairs of indicators from different data sets. Finally, we republish the integrated and predicted values as linked open data.},
}