External Collaborative Research Projects
ACEMS members were involved in many collaborative research projects throughout 2019. These included projects with partners from industry, government, and other sectors. Table 1 below includes a non-exhaustive selection of such projects, highlighting the Centre’s disciplinary depth and breadth across the research themes.
New projects funded under the Industry Collaboration Support Scheme
ACEMS members were also active in 2019 in applying for funding under the Centre’s Industry Collaboration Support Scheme (ICSS) to help support new industry research projects. This scheme strongly encourages cross-node collaboration and applications from the Centre’s early career researchers and Associate Investigators.
Table 2 provides details of the six ICSS applications approved during 2019. These new projects equate to a financial commitment from ACEMS of $97,775 and up to $199,400 in matched funding from external collaborators.
Table 1: A Sample Of ACEMS Collaborative Research Projects Active During 2019
| Research Project Title | External Collaborating Organisation(s) | |
|---|---|---|
| Australian National Cancer Atlas | Cancer Council QLD | |
| Improving the productivity and efficiency of Australian airports | BorderForce, QLD Airports Limited, ISS | |
| Improving our predictive capabilities of stream health | Southeast Queensland Healthy Land and Water | |
| R middleware for immersive experiments and visualisations in VR/AR | CSIRO, EPICentre | |
| Intruder alert! Detecting and classifying events in noise time series | Future Fibre Technologies | |
| Organisational benchmarking | Department of Social Services | |
| Adversarial machine learning for cyber | CSIRO | |
| Quantifying and communicating the impact of uncertainty in complex systems modelling, simulation and analysis. | Defence Science and Technology Group: Weapons and Combat Systems Division | |
| Reef restoration and adaption programme | Australian Institute of Marine Science | |
| High-dimensional inference using extremal-t and extremal skew-t processes | CSIRO | |
| Scheduling optimisation for rotomoulded plastics manufacture | Global Rotomoulding | |
| Statistical machine learning methods | ABS | |
| Optimisation of operations planning for coal export terminals | Aurecon, Newcastle Coal Infrastructure Group, National Energy Resources Association | |
| Fuzzy entropy filtering technology and industrialisation | Hwashen Electronics | |
| Analysing and modelling donor flow in an Australian Red Cross Blood Service donation centre | Australian Red Cross Blood Service | |
| Feature reconstruction from image analysis and visual analytics | CSIRO, EPICentre, Queensland Department of Agriculture and Fisheries | |
| Improving the ability of the Australian cotton industry to report its sustainability performance | Cotton Research and Development Corporation | |
| Visual analytics | CSIRO, EPICentre | |
| Immersive visual analytics for complex and scientific datasets | CSIRO, EPICentre | |
| Genetic risk for osteoporosis | Garvan Institute of Medical Research | |
| New technologies to improve natural resources (biodiversity) on Australian cotton farms | Cotton Research and Development Corporation | |
| Influenza forecasting using online data and its value as evidence in health services evaluation | Australian Red Cross Blood Service | |
| DARPA dengue project | DARPA | |
| Bayesian statistics and machine learning for sports - growing a program of research | Queensland Academy of Sports, Swimming Australia Limited | |
| Assessing solution quality for sequential stochastic optimisation problems | DST Group | |
| Enhancing the outcomes of physical training using models to integrate diverse data under uncertainty | Queensland Academy of Sports, Swimming Australia Limited | |
| Improving 3D printing quality control through computer vision and machine learning | FLEW Solutions | |
| Using machine learning and computer vision to reduce failures in 3D printing | FLEW Solutions | |
| Review of AEMO forecast accuracy metrics | Australian Energy Market Operator (AEMO) | |
| Predictive modelling of Enterococcoi levels in recreational waterways | Healthy Land and Water Ltd | |
| Combining computer vision and data science to improve river monitoring and prediction | Healthy Land and Water Ltd, University of Queensland | |
| Revolutionising water-quality monitoring in the information age. | Queensland Department of Environment and Science, Healthy Land and Water Ltd | |
| A generalised framework for characterising uncertainty in complex systems to enable quantification of extrinsic mathematical uncertainty in defence and emergency services. | Defence Science and Technology Group | |
| Applying deep learning methods to develop models for prediction of animal performance | CSIRO | |
| Impact of continuous drying on key production and performance criteria of engineered wood structural elements | Queensland Department of Agriculture and Fisheries | |
Table 2: New Industry Collaboration Support Scheme Applications Approved In 2019
| Industry Research Project | ACEMS Investigator(s) | External Collaborator(s) |
|---|---|---|
| Visual tools to investigate relationships in multivariate spatiotemporal data with a focus on emergency call data | Dianne Cook and Rob Hyndman (Monash), and Kerrie Mengersen (QUT) | Emily Dodwell (AT&T) |
| A generalised framework for characterising uncertainty in complex systems to enable quantification of extrinsic mathematical uncertainty in defence and emergency services. | Rachael Quill (UoA) and Gentry White (QUT) | Jason Ford and Troy Bruggemann (QUT), and Wayne Power and Edward Dawson (DST Group) |
| Characterisation and prevention of sticker stain when drying Australian hardwoods | Steven Psaltis (QUT) | Adam Redman and Chandan Kumar (DAF) |
| Combining computer vision and data science to improve river monitoring and prediction | Catherine Leigh, Erin Peterson, Kerrie Mengersen, James McGree and Hongbo Xie (QUT) | Paul Maxwell (HL&W), Alistair Grinham (UQ) and Matthew Dunbabin (QUT) |
| Assessing the solution quality of sequential stochastic optimisation problems | Mark Fackrell, Joyce Zhang and Guoqi Qian (UoM) | Jason Looker and David Marlow (DST Group) |
| Bayesian statistics and machine learning for sports – growing a program of research | Paul Wu and Kerrie Mengersen (QUT) | Christine Voge (QAS) |
Abbreviations: DST Group: Defence Science and Technology Group; DAF: Department of Agriculture and Fisheries; HL&W: Healthy Land and Water; and QAS: Queensland Academy of Sport.