This research investigates to what extent ontologies can be used to achieve an accurate classification performance of an automatic text classifier, called the Automatic Classification Engine (ACE). The task of the classifier is to classify Web pages with respect to the Dewey Decimal Classification (DOC) and Library of Congress Classification (LCC) schemes. In particular, this research focuses on how to 1. build a set of ontologies which can provide a mechanism to enable machine reasoning; 2. define the mappings between the ontologies and the two classification schemes; 3. implement an ontology-based classifier. The design and implementation of the classifier concentrates on developing an ontologybased classification model. Given a Web page, the classifier applies the model to carry out reasoning to determine terms - from within the Web page - which represent significant concepts. The classifier, then, uses the mappings to determine the associated DOC and LCC classes of the significant concepts, and assigns the DOC and LCC classes to the Web page. The research also investigates a number of approaches which can be applied to extend the coverage of the ontologies used in a semi-automatic way, since manually constructing ontologies is time consuming. The investigation leads to the design and implementation of a semi-automatic ontology construction system which can recognise new potential terms. By using an ontology editor, those new terms can be integrated into their associated ontologies. An experiment was conducted to validate the effectiveness of the classification model, in which the classifier classified a set of collections of Web pages. The performance of the classifier was measured, in terms of its coverage and accuracy. The experimental evidence shows that the ontology-based automatic text classification approach achieved a better level of performance over the existing approaches.

This thesis investigates Learning Classifier System architectures for decision making in continuous-valued domains. The information contained in continuous-valued domains is not always conveniently expressed using the ternary representation typically used by Learning Classifier Systems and an interval-based representation is a natural choice. Two intervalbased representations recently proposed are analysed, together with their associated operators. Evidence of considerable representational and operator bias is found. A new interval-based representation is proposed that is more straightforward than the previous ones and its bias is analysed. Learning Classifier Systems are compared for online environments that consist of real-valued states and which require every action made by the agent to count towards its performance. Two Learning Classifier System architecture are considered , XCS and ZCS. An interval representation is used for the rule conditions and a roultte wh is used for action selection. The performance of these two Learning Classifier system architectures is investigated on a set of abstract environments with both deterministic and stochastic reward functions. Although XCS clearly delivers superior performance in the deterministic environments tested, the simple ZCS architectur is found to be robust and able to equal or exceed the performance of XCS in the stochastic environments tested, especially those with more demanding characteristics, Aspects of the algorithm and parameter set of ZCS are studied on problems with real-valued states and a Boolean action space. Increased performance is found to result from the use of an update algorithm based on that of NewBoole, an earlier strength-based Learning Classifier System. A new operator, specialize, is introduced and found to be effective in combatting over general classifiers. The modified algorithm and parameter set is tested on several variants of three real-valued test problems The resulting Learning Classifier System is applied to simulated Foreign Exchange trading using an experimental setup and data previously presented in the literature. Results show that a simple Learning Classifier System is able to achieve a positive excess return in simulated trading.

Textual Case Based Reasoning (TCBR) aims at effective reuse of information contained in unstructured documents. The key advantage of TCBR over traditional Information Retrieval systems is its ability to incorporate domain-specific knowledge to facilitate case comparison beyond simple keyword matching. However, substantial human intervention is needed to acquire and transform this knowledge into a form suitable for a TCBR system. In this research, we present automated approaches that exploit statistical properties of document collections to alleviate this knowledge acquisition bottleneck. We focus on two important knowledge containers: relevance knowledge, which shows relatedness of features to cases, and similarity knowledge, which captures the relatedness of features to each other. The terminology is derived from the Case Retrieval Network (CRN) retrieval architecture in TCBR, which is used as the underlying formalism in this thesis applied to text classification. Latent Semantic Indexing (LSI) generated concepts are a useful resource for relevance knowledge acquisition for CRNs. This thesis introduces a supervised LSI technique called "sprinkling" that exploits class knowledge to bias LSI's concept generation. An extension of this idea, called Adaptive Sprinkling has been proposed to handle inter-class relationships in complex domains like hierarchical (e.g. Yahoo directory) and ordinal (e.g. product ranking) classification tasks. Experimental evaluation results show the superiority of CRNs created with sprinkling and AS, not only over LSI on its own, but also over state-of-the-art classifiers like Support Vector Machines (SVM). Current statistical approaches based on feature co-occurrences can be utilized to mine similarity knowledge for CRNs. However, related words often do not co-occur in the same document, though they co-occur with similar words. We introduce an algorithm to efficiently mine such indirect associations, called higher order associations. Empirical results show that CRNs created with the acquired similarity knowledge outperform both LSI and SVM. Incorporating acquired knowledge into the CRN transforms it into a densely connected network. While improving retrieval effectiveness, this has the unintended effect of slowing down retrieval. We propose a novel retrieval formalism called the Fast Case Retrieval Network (FCRN) which eliminates redundant run-time computations to improve retrieval speed. Experimental results show FCRN's ability to scale up over high dimensional textual casebases. Finally, we investigate novel ways of visualizing and estimating complexity of textual casebases that can help explain performance differences across casebases. Visualization provides a qualitative insight into the casebase, while complexity is a quantitative measure that characterizes classification or retrieval hardness intrinsic to a dataset. We study correlations of experimental results from the proposed approaches against complexity measures over diverse casebases.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

The research which forms the basis of this thesis introduces a conceptual model for supporting a case-based reasoning (CBR) selection among decision support systems for strategic asset allocation. Strategic asset allocation is part of an investment policy and is used when choosing an investment portfolio. Strategic asset allocation decision support systems commonly follow a rule-based approach to decision making. The purpose of the conceptual model, introduced by this research, is to support the adoption of a CAR approach, as CAR can be used to produce learning abilities and flexibility. The conceptual model is supported by an intelligent agent framework. Experiments are used to demonstrate the operability of the conceptual model using different decision models. The conceptual model uses case-based learning and flexibility to learn the decision-making processes of different organisations. From evaluations of the conceptual model evidence was found that indicated that intelligent agents and CAR could introduce learning and flexibility into decision support systems used for strategic asset allocation. The conceptual model developed and validated by this research constitutes the research contribution to knowledge.