SONET: a semantic ontological network graph for managing points of interest data heterogeneity
- ORNL
Scalability, standardization, and management are important issues when working with very large Volunteered Geographic Information (VGI). VGI is a rich and valuable source of Points of Interest (POI) information, but its inherent heterogeneity in content, structure, and scale across sources present major challenges for interlinking data sources for analysis. To be useful at scale, the raw information needs to be transformed into a standardized schema that can be easily and reliably used by data analysts. In this work, we tackle the problem of unifying POI categories (e.g. restaurants, temple, and hotel) across multiple data sources to aid in improving land use maps and population distribution estimation as well as support data analysts wishing to fuse multiple data sources with the OpenStreetMap (OSM) mapping platform or working with projects that are already configured in the OSM schema and wish to add additional sources of information. Graph theory and its implementation through the SONET graph database, provides a programmatic way to organize, store, and retrieve standardized POI categories at multiple levels of abstraction. Additionally, it addresses category heterogeneity across data sources by standardizing and managing categories in a way that makes cross-domain analysis possible.
- Research Organization:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-00OR22725
- OSTI ID:
- 1606916
- Resource Relation:
- Conference: 3rd ACM SIGSPATIAL International Workshop on Geospatial Humanities (ACM SIGSPATIAL 2019) - Chicago, Illinois, United States of America - 11/5/2019 10:00:00 AM-11/8/2019 10:00:00 AM
- Country of Publication:
- United States
- Language:
- English
Similar Records
Towards POI-based large-scale land use modeling: spatial scale, semantic granularity, and geographic context
Machine Learning to Improve Retrieval by Category in Big Volunteered Geodata