A Multilayer Semantic Augmentation Model For Geographic Information Applications
Loading...
Links to Files
Permanent Link
Author/Creator
Author/Creator ORCID
Date
2022-01-01
Type of Work
Department
Information Systems
Program
Information Systems
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 see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu
Distribution Rights granted to UMBC by the author.
Access limited to the UMBC community. Item may possibly be obtained via Interlibrary Loan thorugh a local library, pending author/copyright holder's permission.
Distribution Rights granted to UMBC by the author.
Access limited to the UMBC community. Item may possibly be obtained via Interlibrary Loan thorugh a local library, pending author/copyright holder's permission.
Abstract
Current mainstream geographic information systems and maps in general depend on the user’s ability to derive meaning from the multi-layered nature of those maps. A complete answer to the question "what is relevant to my location of interest” should consider the user’s context and include records from multiple Geographical Information System (GIS) layers. The problem this research attempts to solve is the inability of organizations to query geospatial data in a way that conforms with the multi-layered nature of GIS data as well as the topological relationships that can exist between the GIS layers containing those geospatial objects. This dissertations extends the theory behind graphs (or networks) of objects with research into multilayer and semantic link networks to create a formal mathematical model of geographic objects and take advantage of relationships that exist among nodes within a single layer and across multiple layers. This includes the creation of a geospatial ontology that mathematically represents the relationships between different classes of geographic objects. The algorithms in this dissertations take traditional GIS queries and expand them using semantic reasoning and topological rules to include additional geographic objects that are relevant to the user, introducing the concept of a multi-layer Semantically Linked Network (mSLN). This research elevates traditional GIS operations into a common mathematical model to simplify the needs of an organization. This mathematical model has been proven to be correct and a framework based on the model has been designed to be easily implemented by organizations that utilize GIS systems. A prototype system, SAM-GIS has been developed and an empirical evaluation of this framework has been conducted using several real-life case studies relevant to local communities based on data from an actual local government population, along with a performance evaluation of the entire system. Results show that SAM-GIS providesexpanded GIS search results with increased accuracy, precision and recall over those of traditional GIS systems.