An End-to-End Point of Interest (POI) Conflation Framework

Point of interest (POI) data serves as a valuable source of semantic information for places of interest and has many geospatial applications in real estate, transportation, and urban planning. With the availability of different data sources, POI conflation serves as a valuable technique for enrichin...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Raymond Low, Zeynep Duygu Tekler, Lynette Cheah
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	data integration data fusion data conflation volunteered geographic information machine learning natural language processing Geography (General) G1-922
Acceso en línea:	https://doaj.org/article/30ad7bbd750149d6975d541d5444bbca
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:30ad7bbd750149d6975d541d5444bbca
record_format	dspace
spelling	oai:doaj.org-article:30ad7bbd750149d6975d541d5444bbca2021-11-25T17:53:12ZAn End-to-End Point of Interest (POI) Conflation Framework10.3390/ijgi101107792220-9964https://doaj.org/article/30ad7bbd750149d6975d541d5444bbca2021-11-01T00:00:00Zhttps://www.mdpi.com/2220-9964/10/11/779https://doaj.org/toc/2220-9964Point of interest (POI) data serves as a valuable source of semantic information for places of interest and has many geospatial applications in real estate, transportation, and urban planning. With the availability of different data sources, POI conflation serves as a valuable technique for enriching data quality and coverage by merging the POI data from multiple sources. This study proposes a novel end-to-end POI conflation framework consisting of six steps, starting with data procurement, schema standardisation, taxonomy mapping, POI matching, POI unification, and data verification. The feasibility of the proposed framework was demonstrated in a case study conducted in the eastern region of Singapore, where the POI data from five data sources was conflated to form a unified POI dataset. Based on the evaluation conducted, the resulting unified dataset was found to be more comprehensive and complete than any of the five POI data sources alone. Furthermore, the proposed approach for identifying POI matches between different data sources outperformed all baseline approaches with a matching accuracy of 97.6% with an average run time below 3 min when matching over 12,000 POIs to result in 8699 unique POIs, thereby demonstrating the framework’s scalability for large scale implementation in dense urban contexts.Raymond LowZeynep Duygu TeklerLynette CheahMDPI AGarticledata integrationdata fusiondata conflationvolunteered geographic informationmachine learningnatural language processingGeography (General)G1-922ENISPRS International Journal of Geo-Information, Vol 10, Iss 779, p 779 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	data integration data fusion data conflation volunteered geographic information machine learning natural language processing Geography (General) G1-922
spellingShingle	data integration data fusion data conflation volunteered geographic information machine learning natural language processing Geography (General) G1-922 Raymond Low Zeynep Duygu Tekler Lynette Cheah An End-to-End Point of Interest (POI) Conflation Framework
description	Point of interest (POI) data serves as a valuable source of semantic information for places of interest and has many geospatial applications in real estate, transportation, and urban planning. With the availability of different data sources, POI conflation serves as a valuable technique for enriching data quality and coverage by merging the POI data from multiple sources. This study proposes a novel end-to-end POI conflation framework consisting of six steps, starting with data procurement, schema standardisation, taxonomy mapping, POI matching, POI unification, and data verification. The feasibility of the proposed framework was demonstrated in a case study conducted in the eastern region of Singapore, where the POI data from five data sources was conflated to form a unified POI dataset. Based on the evaluation conducted, the resulting unified dataset was found to be more comprehensive and complete than any of the five POI data sources alone. Furthermore, the proposed approach for identifying POI matches between different data sources outperformed all baseline approaches with a matching accuracy of 97.6% with an average run time below 3 min when matching over 12,000 POIs to result in 8699 unique POIs, thereby demonstrating the framework’s scalability for large scale implementation in dense urban contexts.
format	article
author	Raymond Low Zeynep Duygu Tekler Lynette Cheah
author_facet	Raymond Low Zeynep Duygu Tekler Lynette Cheah
author_sort	Raymond Low
title	An End-to-End Point of Interest (POI) Conflation Framework
title_short	An End-to-End Point of Interest (POI) Conflation Framework
title_full	An End-to-End Point of Interest (POI) Conflation Framework
title_fullStr	An End-to-End Point of Interest (POI) Conflation Framework
title_full_unstemmed	An End-to-End Point of Interest (POI) Conflation Framework
title_sort	end-to-end point of interest (poi) conflation framework
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/30ad7bbd750149d6975d541d5444bbca
work_keys_str_mv	AT raymondlow anendtoendpointofinterestpoiconflationframework AT zeynepduygutekler anendtoendpointofinterestpoiconflationframework AT lynettecheah anendtoendpointofinterestpoiconflationframework AT raymondlow endtoendpointofinterestpoiconflationframework AT zeynepduygutekler endtoendpointofinterestpoiconflationframework AT lynettecheah endtoendpointofinterestpoiconflationframework
_version_	1718411855618113536

An End-to-End Point of Interest (POI) Conflation Framework

Ejemplares similares