Return to search

Automated spatial information retrieval and visualisation of spatial data

An increasing amount of freely available Geographic Information System (GIS) data
on the Internet has stimulated recent research into Spatial Information Retrieval (SIR).
Typically, SIR looks at the problem of retrieving spatial data on a dataset by dataset
basis. However in practice, GIS datasets are generally not analysed in isolation. More
often than not multiple datasets are required to create a map for a particular analysis
task. To do this using the current SIR techniques, each dataset is retrieved one by one
using traditional retrieval methods and manually added to the map. To automate map
creation the traditional SIR paradigm of matching a query to a single dataset type
must be extended to include discovering relationships between different dataset types.
This thesis presents a Bayesian inference retrieval framework that will incorporate
expert knowledge in order to retrieve all relevant datasets and automatically create a
map given an initial user query. The framework consists of a Bayesian network that
utilises causal relationships between GIS datasets. A series of Bayesian learning
algorithms are presented that automatically discover these causal linkages from
historic expert knowledge about GIS datasets. This new retrieval model improves
support for complex and vague queries through the discovered dataset relationships.
In addition, the framework will learn which datasets are best suited for particular
query input through feedback supplied by the user.
This thesis evaluates the new Bayesian Framework for SIR. This was achieved by
utilising a test set of queries and responses and measuring the performance of the
respective new algorithms against conventional algorithms. This contribution will
increase the performance and efficiency of knowledge extraction from GIS by
allowing users to focus on interpreting data, instead of focusing on finding which data
is relevant to their analysis. In addition, they will allow GIS to reach non-technical
people.

Identiferoai:union.ndltd.org:ADTP/265732
Date January 2007
CreatorsWalker, Arron R.
PublisherQueensland University of Technology
Source SetsAustraliasian Digital Theses Program
Detected LanguageEnglish

Page generated in 0.0017 seconds