John Fulcher

Computational Intelligence: A Compendium

Computational Intelligence: A Compendium presents a well structured overview about this rapidly growing field with contributions of leading experts in Computational Intelligence. The main focus of the compendium is on applied methods tired-and-proven effective to realworld problems, which is especially useful for practitioners, researchers, students and also newcomers to the field. The 25 chapters are grouped into the following themes: I. Overview and Background II. Data Preprocessing and Systems Integration III. Artificial Intelligence IV. Logic and Reasoning V. Ontology VI. Agents VII. Fuzzy Systems VIII. Artificial Neural Networks IX. Evolutionary Approaches X. DNA and Immune-based Computing.

Face recognition using artificial neural network group-based adaptive tolerance (GAT) trees

Recent artificial neural network research has focused on simple models, but such models have not been very successful in describing complex systems (such as face recognition). This paper introduces the artificial neural network group-based adaptive tolerance (GAT) tree model for translation-invariant face recognition, suitable for use in an airport security system. GAT trees use a two-stage divide-and-conquer tree-type approach. The first stage determines general properties of the input, such as whether the facial image contains glasses or a beard. The second stage identifies the individual. Face perception classification, detection of front faces with glasses and/or beards, and face recognition results using GAT trees under laboratory conditions are presented. We conclude that the neural network group-based model offers significant improvement over conventional neural network trees for this task.

Rainfall estimation using artificial neural network group

Abstract Recent artificial neural network research has focused on simple models, but such models have not proved very successful in describing complex systems. Neural network group theory is a step towards bridging this gap between simple models and complex systems. We first develop artificial neural network group theory, then proceed to show how neural network groups are able to approximate any kind of piecewise continuous function, and to any degree of accuracy. These principles are then illustrated by way of an ANN expert system for rainfall estimation. It is shown that using this approach, rainfall estimates can be computed around 10 times faster than conventional techniques, and with average errors for the overall precipitation event falling below 10%. Based on our work to date, we conclude that neural network group theory holds considerable potential for complex problem solving in various domains.

Consent Mechanisms for Electronic Health Record Systems: A Simple Yet Unresolved Issue

Electronic health record (EHR) systems are now in widespread use in healthcare institutions worldwide. EHRs include sensitive health information and if they are integrated among healthcare providers, data can be accessible from many different sources. This leads to increased concern regarding invasion of privacy and confidentiality. Incorporating consent mechanisms into EHRs has the potential to enhance confidentiality. However there are both positive and negative effects from employing such mechanisms—they need to balance privacy, safety, consumer and public interest.

Mobile Technology Use in Medical Education

This study was undertaken to determine the PDA functionalities for a problem-based learning (PBL) medical curriculum at the Graduate School of Medicine (GSM), the University of Wollongong (UOW). The study determines the factors/aspects of incorporating PDAs, and the attitudes of stakeholders regarding the use of PDAs in such a PBL-based medical curriculum. In-depth interviews were designed and conducted with medical faculty, the medical education technology team and honorary medical academics. Four major PDA functionalities were identified, these being: clinical-log, reference, communication, and general functions. Two major aspects for the incorporation of PDAs into the PBL-medical curriculum at the UOW were determined from the interviews, these being technical and practical aspects. There is a potential for PDAs to be incorporated into the PBL-medical curricula at the UOW. However, a clear strategy needs to be defined as to how best to incorporate PDAs into PBL-medical curricula with minimal impact on students, as well as financial and resource implications for the GSM.

HIGHER ORDER NEURAL NETWORK GROUP MODELS FOR FINANCIAL SIMULATION

Real world financial data is often discontinuous and non-smooth. If we attempt to use neural networks to simulate such functions, then accuracy will be a problem. Neural network group models perform this function much better. Both Polynomial Higher Order Neural network Group (PHONG) and Trigonometric polynomial Higher Order Neural network Group (THONG) models are developed. These HONG models are open box, convergent models capable of approximating any kind of piecewise continuous function, to any degree of accuracy. Moreover they are capable of handling higher frequency, higher order non-linear and discontinuous data. Results obtained using a Higher Order Neural network Group financial simulator are presented, which confirm that HONG group models converge without difficulty, and are considerably more accurate than neural network models (more specifically, around twice as good for prediction, and a factor of four improvement in the case of simulation).

Computational Intelligence: An Introduction

The Artificial Intelligence field continues to be plagued by what can only be described as ‘bold promises for the future syndrome’, often perpetrated by researchers who should know better. While impartial assessment can point to concrete contributions over the past 50 years (such as automated theorem proving, games strategies, the LISP and Prolog high-level computer languages, Automatic Speech Recognition, Natural Language Processing, mobile robot path planning, unmanned vehicles, humanoid robots, data mining, and more), the more cynical argue that AI has witnessed more than its fair share of ‘unmitigated disasters’ during this time – see, for example [3,58,107,125,186]. The general public becomes rapidly jaded with such ‘bold predictions’ that fail to live up to their original hype, and which ultimately render the zealots’ promises as counter-productive.

A technological model to define access to electronic clinical records

This communication describes a functioning model that permits access to an electronic health record across a small number of providers resident in an Australian regional setting. Design criteria designated that provider access rights were to be assignable, revokable, transportable, and informable.

Higher Order Neural Networks for Satellite Weather Prediction

Traditional statistical approaches to modeling and prediction have met with only limited success [30]. As a result, researchers have turned to alternative approaches. In this context, Artificial Neural Networks — ANNs — have received a lot of attention in recent times. Not surprisingly, a lot of this attention has focused on MLPs [2, 7, 24, 31, 39, 43].

Human tracking: a state-of-art survey

Video tracking can be defined as an action which can estimate the trajectory of an object in the image plane as it moves within a scene. A tracker assigns consistent labels to the tracked objects in different frames of a video. The objective of this paper is to provide information on the present state of the art and to discuss future trends in the use of multi-camera tracking systems. In the literature, three main types of multi-camera tracking system have been outlined. The first type relies on challenges in the camera tracking system. The second concerns the methodology of tracking systems in general. The third type relies on current trends in camera tracking systems. We provide an overview of the current research status by summarizing promising avenues for further research.