Hadrian Peter

The Case-Based Neural Network Model and Its Use in Medical Expert Systems

A theoretical model called the Case-Based Neural Network Model is introduced that captures selected patient cases into a data structure which incorporates the fundamental components of expert systems. This data structure is made up of a discrete pattern associative neural network of frames. The Case-Based Neural Network Model is implemented as a computer system called MED2000. This system generates appropriate questions and suggestions based on a notion of diagnosis developed by its neural network and knowledge base. When tested by medical experts, the system was found to be accurate and reproducible.

An Ontology-Based Extraction Framework for a Semantic Web Application

The Semantic Web vision is rapidly becoming a mainstream reality, but obstacles remain in the way. A major challenge is the adoption of practical Semantic Web applications and the production of vast stores of ubiquitous meta-data which is needed to allow robust inference engines to attain the goals of machine readability of web documents. The authors propose the Semantic Web Applications (SEMWAP) framework which facilitates semi-automatic matching of instance data from opaque web databases using lightweight ontology terms. This framework combines information retrieval, information extraction, natural language processing, and ontology techniques to produce a matching and thus provides a viable building block for Semantic Web applications. To experimentally investigate the characteristics and limitations of the SEMWAP framework, a prototype system called the Semantic Ontological Data Labeler (SODL) was constructed.

Integrating Two Artificial Intelligence Theories in a Medical Diagnosis Application

Reasoning Systems (Inference Mechanisms) and Neural Networks are two major areas of Artificial Intelligence (AI). The use of case-based reasoning in Artificial Intelligence systems is well known. Similarly, the AI literature is replete with papers on neural networks. However, there is relatively little research in which the theories of case-based reasoning and neural networks are combined. In this paper we integrate the two theories and show how the resulting model is used in a medical diagnosis application. An implementation of our model provides a valuable prototype for medical experts and medical students alike.

A visualizing application of line integral convolution techniques

Abstract The line integral convolution (LIC) technique, a texture synthesis technique, has served as a useful method for visualizing vector data. However, a number of shortcomings have been identified in the LIC technique, not the least of which are that the technique is computationally expensive and adopts a more or less brute force approach. This paper presents a modification of the original LIC method which addresses these shortcomings. Our method, although used for visualizing atmospheric vortical flows, is also applicable to other atmospheric phenomena. In our method we employ a particular colouring scheme to unambiguously identify the nature of the vortical flows irrespective of the hemisphere in which they occur.