Arron R. Walker

Spatial bayesian learning algorithms for geographic information retrieval

An increasing amount of freely available Geographic Information System (GIS) data on the Internet has stimulated recent research into Geographic Information Retrieval (GIR). Typically, GIR looks at the problem of retrieving GIS datasets on a theme by theme basis. However in practice, themes are generally not analysed in isolation. More often than not multiple themes are required to create a map for a particular analysis task. To do this using the current GIR techniques, each theme is retrieved one by one using traditional retrieval methods and manually added to the map. To automate map creation the traditional GIR paradigm of matching a query to a single theme type must be extended to include discovering relationships between different theme types.Bayesian Inference networks can and have recently been adapted to provide a theme to theme relevance ranking scheme which can be used to automate map creation [2]. The use of Bayesian inference for GIR relies on a manually created Bayesian network. The Bayesian network contains causal probability relationships between spatial themes. The next step in using Bayesian Inference for GIR is to develop algorithms to automatically create a Bayesian network from historical data. This paper discusses a process to utilize conventional Bayesian learning algorithms in GIR. In addition, it proposes three spatial learning Bayesian network algorithms that incorporate spatial relationships between themes into the learning process. The resulting Bayesian networks were loaded into an inference engine that was used to retrieve all relevant themes given a test set of user queries. The performance of the spatial Bayesian learning algorithms were evaluated and compared to performance of conventional non-spatial Bayesian learning 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.

A Bayesian framework for automated dataset retrieval in geographic information systems

Existing geographic information systems (GIS) are intended for expert users and consequently, do not provide any machine intelligence to assist users. This paper presents a Bayesian framework that will incorporate expert knowledge in order to retrieve all relevant datasets given an initial user query. The framework uses a spatial model that combines relational, non-spatial and spatial data. This spatial model allows efficient access of relational linkages for a Bayesian network, and thus improves support for complex and vague queries. The Bayesian network assigns causal probabilities to these relational linkages in order to define expert knowledge of related datasets in the GIS. In addition, the framework will learn which datasets are best suited for particular query input through feedback supplied by the user. 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. The initial user query can be vague and the framework will still be capable of retrieving relevant datasets via the linkages discovered in the Bayesian network.

A framework for a dynamic interactive 3D GIS for non-expert users

Many substantial geographic information systems (GIS) have been designed for use by expert users. As a result, non-expert users often find them difficult to use. This paper presents a framework to facilitate the use of such GIS by non-expert users. The framework achieves this by allowing the creation of vague visual queries which use data abstraction and relevance feedback to obtain a final result. The data abstraction model is dynamically updated to improve future query performance.