A prototype system for the digital lodgement of spatial data

This dissertation develops the model of a prototype system for the digital lodgement of spatial data sets with statutory bodies responsible for the registration and approval of land related actions under the Torrens Title system. Spatial data pertain to the location of geographical entities together with their spatial dimensions and are classified as point, line, area or surface. This dissertation deals with a sub-set of spatial data, land boundary data that result from the activities performed by surveying and mapping organisations for the development of land parcels. The prototype system has been developed, utilising an event-driven paradigm for the user-interface, to exploit the potential of digital spatial data being generated from the utilisation of electronic techniques. The system provides for the creation of a digital model of the cadastral network and dependent data sets for an area of interest from hard copy records. This initial model is calibrated on registered control and updated by field survey to produce an amended model. The field-calibrated model then is electronically validated to ensure it complies with standards of format and content. The prototype system was designed specifically to create a database of land boundary data for subsequent retrieval by land professionals for surveying, mapping and related activities. Data extracted from this database are utilised for subsequent field survey operations without the need to create an initial digital model of an area of interest. Statistical reporting of differences resulting when subsequent initial and calibrated models are compared, replaces the traditional checking operations of spatial data performed by a land registry office. Digital lodgement of survey data is fundamental to the creation of the database of accurate land boundary data. This creation of the database is fundamental also to the efficient integration of accurate spatial data about land being generated by modem technology such as global positioning systems, and remote sensing and imaging, with land boundary information and other information held in Government databases. The prototype system developed provides for the delivery of accurate, digital land boundary data for the land registration process to ensure the continued maintenance of the integrity of the cadastre. Such data should meet also the more general and encompassing requirements of, and prove to be of tangible, longer term benefit to the developing, electronic land information industry.

Automatic speaker recognition under adverse conditions

Speaker verification is the process of verifying the identity of a person by analysing their speech. There are several important applications for automatic speaker verification (ASV) technology including suspect identification, tracking terrorists and detecting a person’s presence at a remote location in the surveillance domain, as well as person authentication for phone banking and credit card transactions in the private sector. Telephones and telephony networks provide a natural medium for these applications. The aim of this work is to improve the usefulness of ASV technology for practical applications in the presence of adverse conditions. In a telephony environment, background noise, handset mismatch, channel distortions, room acoustics and restrictions on the available testing and training data are common sources of errors for ASV systems. Two research themes were pursued to overcome these adverse conditions: Modelling mismatch and modelling uncertainty. To directly address the performance degradation incurred through mismatched conditions it was proposed to directly model this mismatch. Feature mapping was evaluated for combating handset mismatch and was extended through the use of a blind clustering algorithm to remove the need for accurate handset labels for the training data. Mismatch modelling was then generalised by explicitly modelling the session conditions as a constrained offset of the speaker model means. This session variability modelling approach enabled the modelling of arbitrary sources of mismatch, including handset type, and halved the error rates in many cases. Methods to model the uncertainty in speaker model estimates and verification scores were developed to address the difficulties of limited training and testing data. The Bayes factor was introduced to account for the uncertainty of the speaker model estimates in testing by applying Bayesian theory to the verification criterion, with improved performance in matched conditions. Modelling the uncertainty in the verification score itself met with significant success. Estimating a confidence interval for the "true" verification score enabled an order of magnitude reduction in the average quantity of speech required to make a confident verification decision based on a threshold. The confidence measures developed in this work may also have significant applications for forensic speaker verification tasks.

GYAN: A methodology for rule extraction from artificial neural networks

Artificial neural network (ANN) learning methods provide a robust and non-linear approach to approximating the target function for many classification, regression and clustering problems. ANNs have demonstrated good predictive performance in a wide variety of practical problems. However, there are strong arguments as to why ANNs are not sufficient for the general representation of knowledge. The arguments are the poor comprehensibility of the learned ANN, and the inability to represent explanation structures. The overall objective of this thesis is to address these issues by: (1) explanation of the decision process in ANNs in the form of symbolic rules (predicate rules with variables); and (2) provision of explanatory capability by mapping the general conceptual knowledge that is learned by the neural networks into a knowledge base to be used in a rule-based reasoning system. A multi-stage methodology GYAN is developed and evaluated for the task of extracting knowledge from the trained ANNs. The extracted knowledge is represented in the form of restricted first-order logic rules, and subsequently allows user interaction by interfacing with a knowledge based reasoner. The performance of GYAN is demonstrated using a number of real world and artificial data sets. The empirical results demonstrate that: (1) an equivalent symbolic interpretation is derived describing the overall behaviour of the ANN with high accuracy and fidelity, and (2) a concise explanation is given (in terms of rules, facts and predicates activated in a reasoning episode) as to why a particular instance is being classified into a certain category.