A Multi-Feature Based Automatic Approach to Geospatial Record Linking

A Multi-Feature Based Automatic Approach to Geospatial Record Linking

Ying Zhang (School of Control and Computer Engineering, North China Electric Power University, Beijing, China), Puhai Yang (North China Electric Power University, Beijing, China), Chaopeng Li (School of Control and Computer Engineering, North China Electric Power University, Beijing, China), Gengrui Zhang (North China Electric Power University, Beijing, China), Cheng Wang (North China Electric Power University, Beijing, China), Hui He (North China Electric Power University, Beijing, China), Xiang Hu (North China Electric Power University, Beijing, China) and Zhitao Guan (North China Electric Power University, Beijing, China)
Copyright: © 2018 |Pages: 19
DOI: 10.4018/IJSWIS.2018100104

Abstract

This article describes how geographic information systems (GISs) can enable, enrich and enhance geospatial applications and services. Accurate calculation of the similarity among geospatial entities that belong to different data sources is of great importance for geospatial data linking. At present, most research works use the name or category of the entity to measure the similarity of geographic information. Although the geospatial relationship is significant for geographic similarity measure, it has been ignored by most of the previous works. This article introduces the geospatial relationship and topology, and proposes an approach to compute the geospatial record similarity based on multiple features including the geospatial relationships, category and name tags. In order to improve the flexibility and operability, supervised machine learning such as SVM is used for the task of classifying pairs of mapping records. The authors test their approach using three sources, namely, OpenStreetMap, Google and Wikimapia. The results showed that the proposed approach obtained high correlation with the human judgements.
Article Preview

2. Motivation Examples

Let's consider Wikimapia, OpenStreetMap and Google Places as the example sources. Wikimapia provides names, types, latitudes, longitudes and polygon outlines for place entities, while OpenStreetMap gives elevation and address information, such as state and county name, in addition to the place names, amenities, longitudes, latitudes and polygons. In contrast, Google Places presents vicinity besides place names, types, latitudes and longitudes. For the same place, the extracted name from Wikimapia might be totally different from that provided by OpenStreetMap and Google Places. Moreover, for the same place, the location information may differ. For example, one place named “William Jefferson Clinton Middle School” by OpenStreetMap has coordinate “POLYGON((-118.2781488 34.0168423,-118.2771296 34.0163844,-118.2766575 34.0171002,-118.2755567 34.0166202,-118.2747842 34.0178341,-118.2756973 34.0181940,-118.2759215 34.0182743,-118.2757509 34.0185409,-118.2770739 34.0184743,-118.2781488 34.0168423))”. In contrast, the same place is named “Animo Jackie Robinson High School” in Google Places, and its coordinate is “Point(-118.275971,34.017466)”. While, the same place is named “William J. Clinton Middle School” in Wikimapia, and its coordinate is “Point(-118.276482,34.0174013)”.

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 15: 4 Issues (2019): 3 Released, 1 Forthcoming
Volume 14: 4 Issues (2018)
Volume 13: 4 Issues (2017)
Volume 12: 4 Issues (2016)
Volume 11: 4 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing