Semantic web technologies automate geospatial data conflation: Conflating points of interest data for emergency response services
© Springer International Publishing AG 2018. Conflating multiple geospatial data sets into a single dataset is challenging. It requires resolving spatial and aspatial attribute conflicts between source data sets so the best value can be retained and duplicate features removed. Domain experts are abl...
| Main Authors: | , , , |
|---|---|
| Format: | Conference Paper |
| Published: |
2018
|
| Online Access: | http://hdl.handle.net/20.500.11937/66503 |
| _version_ | 1848761338178830336 |
|---|---|
| author | Yu, F. McMeekin, David Arnold, L. West, G. |
| author_facet | Yu, F. McMeekin, David Arnold, L. West, G. |
| author_sort | Yu, F. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | © Springer International Publishing AG 2018. Conflating multiple geospatial data sets into a single dataset is challenging. It requires resolving spatial and aspatial attribute conflicts between source data sets so the best value can be retained and duplicate features removed. Domain experts are able to conflate data using manual comparison techniques, but the task it is labour intensive when dealing with large data sets. This paper demonstrates how semantic technologies can be used to automate the geospatial data conflation process by showcasing how three Points of Interest (POI) data sets can be conflated into a single data set. First, an ontology is generated based on a multipurpose POI data model. Then the disparate source formats are transformed into the RDF format and linked to the designed POI Ontology during the conversion. When doing format transformations, SWRL rules take advantage of the relationships specified in the ontology to convert attribute data from different schemas to the same attribute granularity level. Finally, a chain of SWRL rules are used to replicate human logic and reasoning in the filtering process to find matched POIs and in the reasoning process to automatically make decisions where there is a conflict between attribute values. A conflated POI dataset reduces duplicates and improves the accuracy and confidence of POIs thus increasing the ability of emergency services agencies to respond quickly and correctly to emergency callouts where times are critical. |
| first_indexed | 2025-11-14T10:30:05Z |
| format | Conference Paper |
| id | curtin-20.500.11937-66503 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T10:30:05Z |
| publishDate | 2018 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-665032018-04-30T02:49:04Z Semantic web technologies automate geospatial data conflation: Conflating points of interest data for emergency response services Yu, F. McMeekin, David Arnold, L. West, G. © Springer International Publishing AG 2018. Conflating multiple geospatial data sets into a single dataset is challenging. It requires resolving spatial and aspatial attribute conflicts between source data sets so the best value can be retained and duplicate features removed. Domain experts are able to conflate data using manual comparison techniques, but the task it is labour intensive when dealing with large data sets. This paper demonstrates how semantic technologies can be used to automate the geospatial data conflation process by showcasing how three Points of Interest (POI) data sets can be conflated into a single data set. First, an ontology is generated based on a multipurpose POI data model. Then the disparate source formats are transformed into the RDF format and linked to the designed POI Ontology during the conversion. When doing format transformations, SWRL rules take advantage of the relationships specified in the ontology to convert attribute data from different schemas to the same attribute granularity level. Finally, a chain of SWRL rules are used to replicate human logic and reasoning in the filtering process to find matched POIs and in the reasoning process to automatically make decisions where there is a conflict between attribute values. A conflated POI dataset reduces duplicates and improves the accuracy and confidence of POIs thus increasing the ability of emergency services agencies to respond quickly and correctly to emergency callouts where times are critical. 2018 Conference Paper http://hdl.handle.net/20.500.11937/66503 10.1007/978-3-319-71470-7_6 restricted |
| spellingShingle | Yu, F. McMeekin, David Arnold, L. West, G. Semantic web technologies automate geospatial data conflation: Conflating points of interest data for emergency response services |
| title | Semantic web technologies automate geospatial data conflation: Conflating points of interest data for emergency response services |
| title_full | Semantic web technologies automate geospatial data conflation: Conflating points of interest data for emergency response services |
| title_fullStr | Semantic web technologies automate geospatial data conflation: Conflating points of interest data for emergency response services |
| title_full_unstemmed | Semantic web technologies automate geospatial data conflation: Conflating points of interest data for emergency response services |
| title_short | Semantic web technologies automate geospatial data conflation: Conflating points of interest data for emergency response services |
| title_sort | semantic web technologies automate geospatial data conflation: conflating points of interest data for emergency response services |
| url | http://hdl.handle.net/20.500.11937/66503 |