This thesis investigates the way in which information about the structure of a set of training data with 'natural' characteristics may be used to positively influence the design of associative memory neural network models of the Hopfield type. This is done with a view to reducing the level of connectivity in models of this type. There are three strands to this work. Firstly, an empirical evaluation of the implementation of existing theory is given. Secondly, a number of existing theories are combined to produce novel network models and training regimes. Thirdly, new strategies for constructing and training associative memories based on knowledge of the structure of the training data are proposed. The first conclusion of this work is that, under certain circumstances, performance benefits may be gained by establishing the connectivity in a non-random fashion, guided by the knowledge gained from the structure of the training data. These performance improvements exist in relation to networks in which sparse connectivity is established in a purely random manner. This dilution occurs prior to the training of the network. Secondly, it is verified that, as predicted by existing theory, targeted post-training dilution of network connectivity provides greater performance when compared with networks in which connections are removed at random. Finally, an existing tool for the analysis of the attractor performance of neural networks of this type has been modified and improved. Furthermore, a novel, comprehensive performance analysis tool is proposed.

The field of adaptive hypermedia is a little over a decade old. It has a rich history in a range of fields such as artificial intelligence, user modelling, intelligent tutoring systems and hypertext. Early adaptive hypermedia work concentrated on application-led research; developing a range of systems for specific purposes. In 1996, Peter Brusilovsky reviewed the state-of-the-art and proposed a taxonomy of adaptive hypermedia techniques, thereby providing the means to categorise adaptive hypermedia systems. Since then, several practical frameworks for adaptive hypermedia applications have been produced, in addition to formal models for formalising adaptive hypermedia applications. This thesis presents a new framework for adaptive hypermedia systems based on agent technology, a field of research largely ignored within the adaptive community. Conceptually, this framework occupies a middle ground between the formal reference models for adaptive hypermedia and application-specific frameworks. This framework provides the means to implement formal models using variety of architectural approaches. Three novel adaptive hypermedia applications have been developed around this agent-based framework. Each system employs different architectural structures, they model the user with a variety of profiling techniques, and each provides a different set of adaptive features. The diversity of these three systems emphasises the flexibility and functionality of this proposed agent-based framework.

With computer systems becoming ever larger and more complex, the cost and effort associated with their construction is increasing. Consequently, it is more important than ever that the developers understand how their systems behave if problems are to be avoided. However, acquiring this understanding is a problem: the systems are sufficiently complex that developers need help to analyse and understand them and, at the time this analysis is most crucial, the system is unavailable because it has yet to be built. We already have maturing technologies which address issues associated with the interconnection of software components at the procedural level, but they do not address issues related to the behaviour of these compound systems. Formal, executable models can help here by providing developers with a platform on which to establish the feasibility of a proposed design for a system. However, commercial developers seem reluctant to employ this type of modelling in their design activity. This report describes a new modelling tool in which the traditional model generation technique of writing “programming language like” code is replaced with a model generation tool which uses a graphical representation of models. Despite appearing informal, the system retains sufficient formality to permit the models to be executed using the tool, or converted into code for analysis by a traditional model checking tool.

In this work, a novel method for estimating the relative pose of a known object is presented, which relies on an application-specific data fusion process. A PMD-sensor in conjunction with a CCD-sensor is used to perform the pose estimation. Furthermore, the work provides a method for extending the measurement range of the PMD sensor along with the necessary calibration methodology. Finally, extensive measurements on a very accurate Rendezvous and Docking testbed are made to evaluate the performance, what includes a detailed discussion of lighting conditions. / In der Arbeit wird eine neuartige Methode zur Bestimmung der relativen Lage eines bekannten Objektes vorgestellt, welche auf einem anwendungsspezifischen Datenfusionsprozess basiert. Dabei wird ein PMD-Sensor zusammen mit einem CCD-Sensor benutzt, um die Lagebestimmung vorzunehmen. Darüber hinaus liefert die Arbeit eine Methode, den Messbereich des PMD-Sensors zu erhöhen zusammen mit der notwendigen Kalibrierungsmethoden. Schließlich werden detailierte und weitreichende Messungen aus einer sehr genauen Rendezvous und Docking-Testanlage gemacht, um die Leistungsfähigkeit des Algorithmus zu demonstrieren, was auch eine detaillierte Behandung der Beleuchtungsbedingungen einschließt.

No description available.

Semantic Web data sources such as DBpedia are a rich resource of structured representations of knowledge about geographical features and provide potential data for computing the results of Question Answering System queries that require geo-spatial computations. Retrieval from these resources of all content that is relevant to a particular spatial query of, for example, containment, proximity or crossing is not always straightforward as the geometry is usually confined to point representations and there is considerable inconsistency in the way in which geographical features are referenced to locations. In DBpedia, some geographical feature instances have point coordinates, others have qualitative properties that provide explicit or implicit spatial relationships between named places, and some have neither of these. This thesis demonstrates that structured geo-spatial query, a form of question answering, on DBpedia can be performed with a hybrid query method that exploits quantitative and qualitative spatial properties in combination with a high quality reference geo-dataset that can help to support a full range of geo-spatial query operators such as proximity, containment and crossing as well as vague directional queries such as Find airports north of London?. A quantitative model based on the spatial directional relations in DBpedia has been used to assist in query processing. Evaluation experiments confirm the benefits of combining qualitative and quantitative methods for containment queries and of employing high-quality spatial data, as opposed to DBpedia points, as reference objects for proximity queries, particularly for linear features. The high quality geo-data also enabled answering questions impossible to answer with SemanticWeb resources alone, such as finding geographic features within some distance from a region boundary. The contributions were validated by a prototype geo-spatial query system that combined qualitative and quantitative processing and included ranking answers for directional queries based on models derived from DBpedia contributed data.

No description available.

No description available.

No description available.

No description available.