Dr Paul Wu

Qualifications

• PhD, Avionics, Queensland University of Technology
• MEngSc(Comp&Comm)
• BEng(Elec&Comp)

Research Interests

Develop and apply Bayesian statistical and computational methods to understand and make predictions about complex systems such as ecological, biological and socio-technical systems. Methods include:

• Non-homogeneous state space models
• Bayesian Networks (BNs) and Dynamic Bayesian Networks (DBNs)
• Stochastic queuing models
• Search and optimisation algorithms
• Multi-criteria decision making

Project Description

Some of the work I am currently involved in include:

• Predicting and understanding ecological windows to minimise the impact of human activities on marine ecosystems such as seagrass. An array of methods including non-homogeneous state space models (DBNs), Bayesian multilevel models and other methods such as functional PCA are developed for this. This work is also being used to inform activities such as the Great Barrier Reef integrated monitoring program. It involves a broad collaboration with AIMS, WAMSI, ECU, UWA, JCU, regulators in Qld and WA, and international collaborators.
• Benchmarking of social services to support managers and policy makers in improving performance.
• A program of research in sports including predictive modelling of fatigue using PCA and the countermovement jump, analysis of posture control, and addressing the challenges of longitudinal data with wearable technologies. This is a collaboration with the AIS.
• Predicting and supporting the management of queues and passenger flows in airports through development of inhomogeneous queuing models and Approximate Bayesian Computation. This is a linkage project with Brisbane Airport, Gold Coast Airport, Border Force and ISS.
• Healthy waterways project, supporting the design of policy and advice for safe use of public swim sites such as beaches, estuaries and lakes. This is for city councils in the region south-east Queensland region.

Publications

Selected publications (for more, please see my Google Scholar profile and QUT eprints):

Wu, P. P.-Y., Mengersen, K., McMahon, K., Kendrick, G. A., Chartrand, K., York, P. H., Caley, M. J. (2017). Timing anthropogenic stressors to mitigate their impact on marine ecosystem resilience. Nature Communications, In Press.

Wu, P. P.-Y., Caley, M. J., Kendrick, G. A., McMahon, K., & Mengersen, K. (2017). Dynamic Bayesian Network inferencing for non-homogeneous complex systems. Journal of the Royal Statistical Society, Series C, .

Wu, P. P.-Y., McMahon, K., Rasheed, M. A., Kendrick, G. A., York, P. H., Chartrand, K., Mengersen, K. (2017). Managing seagrass resilience under cumulative dredging disturbances: Predicting risk using dynamic Bayesian networks. Journal of Applied Ecology, In Press.

Wu, Paul P., Fookes, Clinton, Pitchforth, Jegar, & Mengersen, Kerrie (2015) A Framework for Model Integration and Holistic Modelling of Socio-Technical Systems. Decision Support Systems, 71, pp. 14-27.

Wu, Paul P., Pitchforth, Jegar, Mengersen, Kerrie (2014) A Hybrid Queue-based Bayesian Network framework for passenger facilitation modelling. Transportation Research Part C: Emerging Technologies, 46, pp. 247-260.

Pitchforth, Jegar, Wu, Paul P., & Mengersen, Kerrie (2014) Applying a validation framework to a working airport terminal model. Expert Systems with Applications, 41(9), pp. 4388-4400.

Wu, Paul P. & Mengersen, Kerrie (2013) A review of models and model usage scenarios for an airport complex system. Transportation Research Part A: Policy and Practice, 47, pp. 124-140.

Wu, Paul P., Campbell, Duncan A., & Merz, Torsten (2011) Multi-objective four-dimensional vehicle motion planning in large dynamic environments. IEEE Transactions on Systems, Man and Cybernetics Part B: Cybernetics, 41(3), pp. 621-634.

Contact Details

p.wu@qut.edu.au

About

I am an engineer turned statistician who gets to work on exciting projects across many disciplines with really cool people. Last year, I was awarded a visiting fellow scholarship to ECU.

Past Projects

• Online decision support for managers and decision makers in the airport environment for passenger facilitation (part of the Airports of the Future linkage project with Customs and Border Protection, Brisbane Airport and others)
• Modelling of risk presented to people on the ground due to overflight of unmanned aircraft (for the DSTO)