Enhancing spatial query results using semantics and multiplex networks
No Thumbnail Available
Links to Files
Permanent Link
Author/Creator
Author/Creator ORCID
Date
2018
Type of Work
Department
Program
Citation of Original Publication
Rights
This item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please contact the author.
Abstract
Geographic information retrieval (GIR) research mainly focuses on finding relevant geographic artifacts along one layer, although answers to queries should preferably include artifacts across multiple layers.This paper addresses this limitation, by exploiting relationships that exist between geographical objects of the same or different types. Given the existence of these relationships we can infer additional indirect semantic relationships between geographical objects that otherwise would be ignored. This semantic information contains multiple dimensions. This research creates a mathematical model of semantically relevant geographic objects that belong to different layers using the construct of multiplex networks. The proposed model respects and extends the “layered” structure of geographic data, and enhances the results of queries made to a GIS. A prototype system has been implemented over an existing GIS relational database. Experiments with the prototype show significant improvements in the results of queries, measured using precision and recall.