ORCID Profile
0000-0002-6694-9572
Current Organisation
University of Queensland
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Research Topics
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Top 5 Research Topics
ANZSRC Field of Research (FoR)
Artificial Intelligence and Image Processing | Neural Networks, Genetic Alogrithms And Fuzzy Logic | Health Information Systems (incl. Surveillance) | Pattern Recognition and Data Mining | Manufacturing Engineering | Health Information Systems (Incl. Surveillance) | Robotics And Mechatronics | Aerospace Structures | Flexible Manufacturing Systems | Astronomy And Astrophysics |
ANZSRC Socio-Economic Objective (SEO)
Expanding Knowledge in the Information and Computing Sciences | Health and Support Services not elsewhere classified | Information processing services | Health and support services not elsewhere classified | Higher education | Industrial machinery and equipment | Physical sciences | Machined products | Aerospace equipment
Related Links
Publications
Applying machine learning to catalogue matching in astrophysics
Publisher: Oxford University Press (OUP)
Date: 06-2005
The turing test track of the 2012 Mario AI Championship: Entries and evaluation
Publisher: IEEE
Date: 08-2013
Length scale for characterising continuous optimization problems
Publisher: Springer Berlin Heidelberg
Date: 2012
Convergence analysis of UMDAC with finite populations: A case study on flat landscapes
Publisher: ACM
Date: 08-07-2009
Multi-layer Perceptron Error Surfaces: Visualization, Structure and Modelling
Publisher: University of Queensland Library
Date: 2000
DOI: 10.14264/157842
Use of freely available datasets and machine learning methods in predicting deforestation
Publisher: Elsevier BV
Date: 2017
Game designers training first person shooter bots
Publisher: Springer Berlin Heidelberg
Date: 2012
Neural networks and the classification of mineralogical samples using x-ray spectra
Publisher: IEEE
Date: 2002
Visualization of learning in multilayer perceptron networks using principal component analysis
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2003
Matching of catalogues by probabilistic pattern classification
Publisher: Oxford University Press (OUP)
Date: 08-05-2006
Unsupervised DRG upcoding detection in healthcare databases
Publisher: IEEE
Date: 12-2010
Beware the parameters: Estimation of distribution algorithms applied to circles in a square packing
Publisher: Springer Berlin Heidelberg
Date: 2012
Exploring the MLDA benchmark on the Nevergrad platform
Publisher: ACM
Date: 13-07-2019
Variable screening for reduced dependency modelling in Gaussian-based continuous Estimation of Distribution Algorithms
Publisher: IEEE
Date: 06-2012
Empirical evidence for ultrametric structure in multi-layer perceptron error surfaces
Publisher: Springer Science and Business Media LLC
Date: 2002
Parameter-free search of time-series discord
Publisher: Springer Science and Business Media LLC
Date: 03-2013
Network Analysis and Visualisation of Opioid Prescribing Data
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2020
Machine learning vs addiction therapists: A pilot study predicting alcohol dependence treatment outcome from patient data in behavior therapy with adjunctive medication
Publisher: Elsevier BV
Date: 04-2019
DOI: 10.1016/J.JSAT.2019.01.020
Abstract: Clinical staff providing addiction treatment predict patient outcome poorly. Prognoses based on linear statistics are rarely replicated. Addiction is a complex non-linear behavior. Incorporating non-linear models, Machine Learning (ML) has successfully predicted treatment outcome when applied in other areas of medicine. Using identical assessment data across the two groups, this study compares the accuracy of ML models versus clinical staff to predict alcohol dependence treatment outcome in behavior therapy using patient data only. Machine learning models (n = 28) were constructed ('trained') using demographic and psychometric assessment data from 780 previously treated patients who had undertaken a 12 week, abstinence-based Cognitive Behavioral Therapy program for alcohol dependence. Independent predictions applying assessment data for an additional 50 consecutive patients were obtained from 10 experienced addiction therapists and the 28 trained ML models. The predictive accuracy of the ML models and the addiction therapists was then compared with further investigation of the 10 best models selected by cross-validated accuracy on the training-set. Variables selected as important for prediction by staff and the most accurate ML model were examined. The most accurate ML model (Fuzzy Unordered Rule Induction Algorithm, 74%) was significantly more accurate than the four least accurate clinical staff (51%-40%). However, the robustness of this finding may be limited by the moderate area under the receiver operator curve (AUC = 0.49). There was no significant difference in mean aggregate predictive accuracy between 10 clinical staff (56.1%) and the 28 best models (58.57%). Addiction therapists favoured demographic and consumption variables compared with the ML model using more questionnaire subscales. The majority of staff and ML models were not more accurate than suggested by chance. However, the best performing prediction models may provide useful adjunctive information to standard clinically available prognostic data to more effectively target treatment approaches in clinical settings.
Detecting contaminated birthdates using generalized additive models
Publisher: Springer Science and Business Media LLC
Date: 12-06-2014
Exploratory Analysis of Clustering Problems Using a Comparison of Particle Swarm Optimization and Differential Evolution
Publisher: Springer International Publishing
Date: 27-12-2016
On building a principled framework for evaluating and testing evolutionary algorithms: A continuous landscape generator
Publisher: IEEE
Date: 2003
On the importance of diversity maintenance in estimation of distribution algorithms
Publisher: ACM
Date: 25-11-2021
A model-based framework for black-box problem comparison using gaussian processes
Publisher: Springer International Publishing
Date: 2018
Flood-fill Q-learning updates for learning redundant policies in order to interact with a computer screen by clicking
Publisher: Springer International Publishing
Date: 2018
Direct feature evaluation in black-box optimization using problem transformations
Publisher: MIT Press
Date: 03-2018
DOI: 10.1162/EVCO_A_00247
Abstract: Exploratory Landscape Analysis provides s le-based methods to calculate features of black-box optimization problems in a quantitative and measurable way. Many problem features have been proposed in the literature in an attempt to provide insights into the structure of problem landscapes and to use in selecting an effective algorithm for a given optimization problem. While there has been some success, evaluating the utility of problem features in practice presents some significant challenges. Machine learning models have been employed as part of the evaluation process, but they may require additional information about the problems as well as having their own hyper-parameters, biases and experimental variability. As a result, extra layers of uncertainty and complexity are added into the experimental evaluation process, making it difficult to clearly assess the effect of the problem features. In this article, we propose a novel method for the evaluation of problem features which can be applied directly to in idual or groups of features and does not require additional machine learning techniques or confounding experimental factors. The method is based on the feature's ability to detect a prior ranking of similarity in a set of problems. Analysis of Variance (ANOVA) significance tests are used to determine if the feature has successfully distinguished the successive problems in the set. Based on ANOVA test results, a percentage score is assigned to each feature for different landscape characteristics. Experimental results for twelve different features on four problem transformations demonstrate the method and provide quantitative evidence about the ability of different problem features to detect specific properties of problem landscapes.
An agent based approach to examining shared situation awareness
Publisher: IEEE
Date: 2007
An empirical study of the sample size variability of Optimal Active Learning using gaussian process regression
Publisher: IEEE
Date: 06-2008
Under voltage load shedding in power systems with wind turbine-driven doubly fed induction generators
Publisher: Elsevier BV
Date: 03-2013
Regional-scale, fully coupled modelling of stream-aquifer interaction in a tropical catchment
Publisher: Elsevier BV
Date: 09-2006
Parameter interdependence and uncertainty induced by lumping in a hydrologic model
Publisher: American Geophysical Union (AGU)
Date: 05-2007
DOI: 10.1029/2006WR005347
Combining meta-EAs and racing for difficult EA parameter tuning tasks
Publisher: Springer Berlin Heidelberg
Date: 2007
Using regression models for characterizing and comparing black box optimization problems
Publisher: Elsevier BV
Date: 02-2022
Sampling techniques and distance metrics in high dimensional continuous landscape analysis: Limitations and improvements
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2014
Bayesian inference in estimation of distribution algorithms
Publisher: IEEE
Date: 09-2007
An improved small-sample statistical test for comparing the success rates of evolutionary algorithms
Publisher: ACM
Date: 08-07-2009
Towards improved benchmarking of black-box optimization algorithms using clustering problems
Publisher: Springer Science and Business Media LLC
Date: 10-03-2016
Playing in continuous spaces: Some analysis and extension of population-based incremental learning
Publisher: IEEE
Date: 2003
MRI magnet design: Search space analysis, EDAs and a real-world problem with significant dependencies
Publisher: ACM
Date: 25-06-2005
Using landscape topology to compare continuous metaheuristics: A framework and case study on EDAs and ridge structure
Publisher: MIT Press - Journals
Date: 06-2012
DOI: 10.1162/EVCO_A_00070
Abstract: In this paper we extend a previously proposed randomized landscape generator in combination with a comparative experimental methodology to study the behavior of continuous metaheuristic optimization algorithms. In particular, we generate two-dimensional landscapes with parameterized, linear ridge structure, and perform pairwise comparisons of algorithms to gain insight into what kind of problems are easy and difficult for one algorithm instance relative to another. We apply this methodology to investigate the specific issue of explicit dependency modeling in simple continuous estimation of distribution algorithms. Experimental results reveal specific ex les of landscapes (with certain identifiable features) where dependency modeling is useful, harmful, or has little impact on mean algorithm performance. Heat maps are used to compare algorithm performance over a large number of landscape instances and algorithm trials. Finally, we perform a meta-search in the landscape parameter space to find landscapes which maximize the performance between algorithms. The results are related to some previous intuition about the behavior of these algorithms, but at the same time lead to new insights into the relationship between dependency modeling in EDAs and the structure of the problem landscape. The landscape generator and overall methodology are quite general and extendable and can be used to examine specific features of other algorithms.
Parallel evolutionary algorithm for single and multi-objective optimisation: Differential evolution and constraints handling
Publisher: Elsevier BV
Date: 12-2017
Reinforcement learning in first person shooter games
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2011
Predicting alcohol dependence treatment outcomes: a prospective comparative study of clinical psychologists versus ‘trained’ machine learning models
Publisher: Wiley
Date: 26-03-2020
DOI: 10.1111/ADD.15038
Astronomical catalogue matching as a mixture model problem
Publisher: AIP
Date: 2012
DOI: 10.1063/1.4759615
Estimating the intensity of ward admission and its effect on emergency department access block
Publisher: Wiley
Date: 21-11-2012
DOI: 10.1002/SIM.5684
Abstract: Emergency department access block is an urgent problem faced by many public hospitals today. When access block occurs, patients in need of acute care cannot access inpatient wards within an optimal time frame. A widely held belief is that access block is the end product of a long causal chain, which involves poor discharge planning, insufficient bed capacity, and inadequate admission intensity to the wards. This paper studies the last link of the causal chain-the effect of admission intensity on access block, using data from a metropolitan hospital in Australia. We applied several modern statistical methods to analyze the data. First, we modeled the admission events as a nonhomogeneous Poisson process and estimated time-varying admission intensity with penalized regression splines. Next, we established a functional linear model to investigate the effect of the time-varying admission intensity on emergency department access block. Finally, we used functional principal component analysis to explore the variation in the daily time-varying admission intensities. The analyses suggest that improving admission practice during off-peak hours may have most impact on reducing the number of ED access blocks.
Creating a multi-purpose first person shooter bot with reinforcement learning
Publisher: IEEE
Date: 12-2008
Analysing and characterising optimization problems using length scale
Publisher: Springer Science and Business Media LLC
Date: 25-09-2017
Multiple community energy storage planning in distribution networks using a cost-benefit analysis
Publisher: Elsevier BV
Date: 03-2017
A general-purpose tunable landscape generator
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2006
Evolving Pac-Man Players: Can We Learn from Raw Input?
Publisher: IEEE
Date: 2007
Modularity Based Linkage Model For Neuroevolution
Publisher: ACM
Date: 15-07-2023
Interactively training first person shooter bots
Publisher: IEEE
Date: 09-2012
Parameter estimation and uncertainty analysis for a watershed model
Publisher: Elsevier BV
Date: 07-2007
Population-Based Continuous Optimization, Probabilistic Modelling and Mean Shift
Publisher: MIT Press - Journals
Date: 03-2005
Abstract: Evolutionary algorithms perform optimization using a population of s le solution points. An interesting development has been to view population-based optimization as the process of evolving an explicit, probabilistic model of the search space. This paper investigates a formal basis for continuous, population-based optimization in terms of a stochastic gradient descent on the Kullback-Leibler ergence between the model probability density and the objective function, represented as an unknown density of assumed form. This leads to an update rule that is related and compared with previous theoretical work, a continuous version of the population-based incremental learning algorithm, and the generalized mean shift clustering framework. Experimental results are presented that demonstrate the dynamics of the new algorithm on a set of simple test problems.
When does dependency modelling help? Using a randomized landscape generator to compare algorithms in terms of problem structure
Publisher: Springer Berlin Heidelberg
Date: 2010
Comparison of CPF and modal analysis methods in determining effective DG locations
Publisher: IEEE
Date: 10-2010
Using Gaussian process with test rejection to detect T-cell epitopes in pathogen genomes
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2010
Intra-task Curriculum Learning for Faster Reinforcement Learning in Video Games
Publisher: Springer International Publishing
Date: 2018
Fitness Landscape Analysis in Data-Driven Optimization: An Investigation of Clustering Problems
Publisher: IEEE
Date: 06-2019
An influence map model for playing Ms. Pac-Man
Publisher: IEEE
Date: 12-2008
The importance of implementation details and parameter settings in black-box optimization: a case study on Gaussian estimation-of-distribution algorithms and circles-in-a-square packing problems
Publisher: Springer Science and Business Media LLC
Date: 15-10-2018
Quantitative measure of nonconvexity for black-box continuous functions
Publisher: Elsevier BV
Date: 02-2019
Characterisation of sea-water intrusion in the Pioneer Valley, Australia using hydrochemistry and three-dimensional numerical modelling
Publisher: Springer Science and Business Media LLC
Date: 25-10-2006
Learning to play Pac-Man: An evolutionary, rule-based approach
Publisher: IEEE
Date: 2003
Related Organisations
Related Funding Activities
Linkage Projects - Grant ID: LP0776417
Start Date: 06-2008
End Date: 12-2012
Amount: $126,728.00
Funder: Australian Research Council
View Funded ActivityLinkage Projects - Grant ID: LP160100722
Start Date: 12-2016
End Date: 06-2020
Amount: $191,000.00
Funder: Australian Research Council
View Funded ActivitySpecial Research Initiatives - Grant ID: SR0567109
Start Date: 09-2005
End Date: 09-2006
Amount: $69,438.00
Funder: Australian Research Council
View Funded ActivityLinkage Projects - Grant ID: LP120200121
Start Date: 03-2013
End Date: 12-2016
Amount: $150,000.00
Funder: Australian Research Council
View Funded ActivityLinkage Projects - Grant ID: LP0560347
Start Date: 2005
End Date: 06-2008
Amount: $74,944.00
Funder: Australian Research Council
View Funded Activity