Collecting, Integrating, Enriching and Republishing Open City Data as Linked Data. Bischof, S., Martin, C., Polleres, A., & Schneider, P. In Arenas, M., Corcho, O., Simperl, E., Strohmaier, M., d'Aquin , M., Srinivas, K., Groth, P. T., Dumontier, M., Heflin, J., Thirunarayan, K., & Staab, S., editors, Proceedings of the 14th International Semantic Web Conference (ISWC 2015) - Part II, volume 9367, of Lecture Notes in Computer Science (LNCS), pages 57-75, Bethlehem, Pennsylvania, October, 2015. Springer. Paper abstract bibtex 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.
@inproceedings{bisc-etal-2015ISWC,
author = {Stefan Bischof and Christoph Martin and Axel Polleres and Patrik Schneider},
Booktitle = {Proceedings of the 14th International Semantic Web Conference (ISWC 2015) - Part II},
year = 2015,
month = oct,
day = {11--15},
address = {Bethlehem, Pennsylvania},
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.},
title = {Collecting, Integrating, Enriching and Republishing Open City Data as Linked Data},
url = {http://www.polleres.net/publications/bisc-etal-2015ISWC.pdf},
series = LNCS,
volume = 9367,
editor = {Marcelo Arenas and Oscar Corcho and Elena Simperl and Markus Strohmaier and Mathieu d'Aquin and Kavitha Srinivas and Paul T. Groth and Michel Dumontier and Jeff Heflin and Krishnaprasad Thirunarayan and Steffen Staab},
publisher = {Springer},
pages = {57-75}
}
Downloads: 0
{"_id":"JJedXqGeB4EqRKp3x","bibbaseid":"bischof-martin-polleres-schneider-collectingintegratingenrichingandrepublishingopencitydataaslinkeddata-2015","downloads":0,"creationDate":"2015-12-08T08:58:02.534Z","title":"Collecting, Integrating, Enriching and Republishing Open City Data as Linked Data","author_short":["Bischof, S.","Martin, C.","Polleres, A.","Schneider, P."],"year":2015,"bibtype":"inproceedings","biburl":"www.polleres.net/mypublications.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Stefan"],"propositions":[],"lastnames":["Bischof"],"suffixes":[]},{"firstnames":["Christoph"],"propositions":[],"lastnames":["Martin"],"suffixes":[]},{"firstnames":["Axel"],"propositions":[],"lastnames":["Polleres"],"suffixes":[]},{"firstnames":["Patrik"],"propositions":[],"lastnames":["Schneider"],"suffixes":[]}],"booktitle":"Proceedings of the 14th International Semantic Web Conference (ISWC 2015) - Part II","year":"2015","month":"October","day":"11–15","address":"Bethlehem, Pennsylvania","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.","title":"Collecting, Integrating, Enriching and Republishing Open City Data as Linked Data","url":"http://www.polleres.net/publications/bisc-etal-2015ISWC.pdf","series":"Lecture Notes in Computer Science (LNCS)","volume":"9367","editor":[{"firstnames":["Marcelo"],"propositions":[],"lastnames":["Arenas"],"suffixes":[]},{"firstnames":["Oscar"],"propositions":[],"lastnames":["Corcho"],"suffixes":[]},{"firstnames":["Elena"],"propositions":[],"lastnames":["Simperl"],"suffixes":[]},{"firstnames":["Markus"],"propositions":[],"lastnames":["Strohmaier"],"suffixes":[]},{"firstnames":["Mathieu"],"propositions":["d'Aquin"],"lastnames":[],"suffixes":[]},{"firstnames":["Kavitha"],"propositions":[],"lastnames":["Srinivas"],"suffixes":[]},{"firstnames":["Paul","T."],"propositions":[],"lastnames":["Groth"],"suffixes":[]},{"firstnames":["Michel"],"propositions":[],"lastnames":["Dumontier"],"suffixes":[]},{"firstnames":["Jeff"],"propositions":[],"lastnames":["Heflin"],"suffixes":[]},{"firstnames":["Krishnaprasad"],"propositions":[],"lastnames":["Thirunarayan"],"suffixes":[]},{"firstnames":["Steffen"],"propositions":[],"lastnames":["Staab"],"suffixes":[]}],"publisher":"Springer","pages":"57-75","bibtex":"@inproceedings{bisc-etal-2015ISWC,\n author = {Stefan Bischof and Christoph Martin and Axel Polleres and Patrik Schneider},\n Booktitle = {Proceedings of the 14th International Semantic Web Conference (ISWC 2015) - Part II},\n year = 2015,\n month = oct,\n day = {11--15},\n address = {Bethlehem, Pennsylvania},\n abstract = {Access to high quality and recent data is crucial both for\ndecision makers in cities as well as for the public.\nLikewise, infrastructure providers could offer more tailored solutions\nto cities based on such data. However, even though there are many data\nsets containing relevant indicators about cities available as open\ndata, it is cumbersome to integrate and analyze them, since the\ncollection is still a manual process and the sources are not connected\nto each other upfront. Further, disjoint indicators and cities across\nthe available data sources lead to a large proportion of missing\nvalues when integrating these sources. In this paper we present a platform for collecting, integrating, and\nenriching open data about cities in a reusable and comparable manner:\nwe have integrated various open data sources and present approaches\nfor predicting missing values, where we use standard regression\nmethods in combination with principal component analysis (PCA) to\nimprove quality and amount of predicted values. Since indicators and\ncities only have partial overlaps across data sets, we particularly\nfocus on predicting indicator values across data sets, where we\nextend, adapt, and evaluate our prediction model for this particular\npurpose: as a ``side product'' we learn ontology mappings (simple equations and sub-properties) for pairs of indicators from different\ndata sets. Finally, we republish the integrated and predicted values\nas linked open data.},\n title = {Collecting, Integrating, Enriching and Republishing Open City Data as Linked Data},\n url = {http://www.polleres.net/publications/bisc-etal-2015ISWC.pdf},\n series = LNCS,\n volume = 9367,\n editor = {Marcelo Arenas and Oscar Corcho and Elena Simperl and Markus Strohmaier and Mathieu d'Aquin and Kavitha Srinivas and Paul T. Groth and Michel Dumontier and Jeff Heflin and Krishnaprasad Thirunarayan and Steffen Staab},\n publisher = {Springer},\n pages = {57-75}\n} \n\n\n","author_short":["Bischof, S.","Martin, C.","Polleres, A.","Schneider, P."],"editor_short":["Arenas, M.","Corcho, O.","Simperl, E.","Strohmaier, M.","d'Aquin , M.","Srinivas, K.","Groth, P. T.","Dumontier, M.","Heflin, J.","Thirunarayan, K.","Staab, S."],"key":"bisc-etal-2015ISWC","id":"bisc-etal-2015ISWC","bibbaseid":"bischof-martin-polleres-schneider-collectingintegratingenrichingandrepublishingopencitydataaslinkeddata-2015","role":"author","urls":{"Paper":"http://www.polleres.net/publications/bisc-etal-2015ISWC.pdf"},"metadata":{"authorlinks":{"polleres, a":"https://bibbase.org/show?bib=www.polleres.net/mypublications.bib"}},"downloads":0,"html":""},"search_terms":["collecting","integrating","enriching","republishing","open","city","data","linked","data","bischof","martin","polleres","schneider"],"keywords":[],"authorIDs":["FyLDFGg993nDS2Spf"],"dataSources":["cBfwyqsLFQQMc4Fss","gixxkiKt6rtWGoKSh","QfLT6siHZuHw9MqvK"]}