Automatic geospatial data conflation using semantic web technologies

Fu-wei, YU; West, Geoff; Arnold, Lesley M.; McMeekin, David A.; Moncrieff, Simon

doi:10.1145/2843043.2843375

Cited by 7 publications

(6 citation statements)

References 90 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Input datasets used in this process were available through various access methods (some via OGC CSW and others as raw data download) and part of the solution was the SKI Broker's intelligence, as described in Section 3.2.4. This example confirms that such a solution is possible only with an SKI and not with SDIs (Yu et al, 2016(Yu et al, , 2018.…”

Section: Ski As Enabler Of Knowledge On-demandsupporting

confidence: 70%

From spatial data to spatial knowledge infrastructure: A proposed architecture

Ivánová

McMeekin

et al. 2020

Transactions in GIS

View full text Add to dashboard Cite

Spatial data infrastructures (SDIs) provide access to spatial data and services for humans to solve spatial problems but represent a barrier for machines such as search engines or spatial services. In this article we propose an architecture for spatial knowledge infrastructure (SKI), which attempts to overcome these limitations, and describe the interactions between its components. The SKI architecture proposed is illustrated for two scenarios. The first is an architecture for an ideal solution requiring spatial data on the web, and the second is for a practical short‐term solution that takes into consideration legacy SDIs as well as spatial data on the web in its implementation. In addition, the utility of the proposed SKI architecture is illustrated with two examples demonstrating the scope of the SKI in two different ways: where the SKI is a “knowledge enabler,” and where the SKI acts as a “knowledge creator.” A discussion on how well the proposed architecture meets current best practice for spatial data on the web, as well as obstacles and challenges in the implementation of the proposed solutions, concludes the article.

show abstract

Section: Ski As Enabler Of Knowledge On-demandsupporting

confidence: 70%

From spatial data to spatial knowledge infrastructure: A proposed architecture

Ivánová

McMeekin

et al. 2020

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…Xia et al (2014) considered two POIs to be a match if they are the nearest neighbor based on spatial distance, and their name and address similarity is higher than 0.6. Similar POI matching rules were also defined in other studies (Lamprianidis et al, 2014;F. Yu et al, 2016).…”

Section: Rule-based Approachesmentioning

confidence: 88%

Conflating point of interest (POI) data: A systematic review of matching methods

Sun

et al. 2023

Computers, Environment and Urban Systems

View full text Add to dashboard Cite

“…Yu et al [17] used ontologies in Web Ontology Language 2 (OWL-2) (https://www.w3 .org/TR/owl2-overview/ (accessed on 10 December 2021)) and Description Logic (DL) to build their data conflation framework. Ontologies were used to represent spatial datasets and relevant geometries and topologies.…”

Section: Related Workmentioning

confidence: 99%

A System for Aligning Geographical Entities from Large Heterogeneous Sources

Melo

Er-Rahmadi

Pan

2022

IJGI

View full text Add to dashboard Cite

Aligning points of interest (POIs) from heterogeneous geographical data sources is an important task that helps extend map data with information from different datasets. This task poses several challenges, including differences in type hierarchies, labels (different formats, languages, and levels of detail), and deviations in the coordinates. Scalability is another major issue, as global-scale datasets may have tens or hundreds of millions of entities. In this paper, we propose the GeographicaL Entities AligNment (GLEAN) system for efficiently matching large geographical datasets based on spatial partitioning with an adaptable margin. In particular, we introduce a text similarity measure based on the local-context relevance of tokens used in combination with sentence embeddings. We then come up with a scalable type embedding model. Finally, we demonstrate that our proposed system can efficiently handle the alignment of large datasets while improving the quality of alignments using the proposed entity similarity measure.

show abstract

Automatic geospatial data conflation using semantic web technologies

Cited by 7 publications

References 90 publications

From spatial data to spatial knowledge infrastructure: A proposed architecture

From spatial data to spatial knowledge infrastructure: A proposed architecture

Conflating point of interest (POI) data: A systematic review of matching methods

A System for Aligning Geographical Entities from Large Heterogeneous Sources

Contact Info

Product

Resources

About