Aprof Douglas Creighton
|Position:||Associate Professor (Research)|
|Faculty or Division:||Office of the Deputy Vice-Chancellor (Research)|
|Department:||Centre for Intelligent Systems Research|
|Campus:||Geelong Waurn Ponds Campus|
|Phone:||+61 3 52272179 +61 3 52272179|
Dr Doug Creighton is a lead researcher in the largest research team in the field of simulation, optimisation and scheduling for infrastructure, security, materials handling and manufacturing systems in Australia. His research focus is algorithms and methodologies to improve estimation and performance of complex systems operating under uncertainty, variability and continuous change.
Dr Creighton is actively involved in process simulation, empirical modelling, soft computing, human machine interface and simulation-based optimisation research. He has expertise and domain knowledge in a broad range of industrial sectors, including manufacturing, logistics, airports, warehousing, energy and mining.
Dr Creighton received a B.Eng. (Honours) in Systems Engineering and a B.Sc. in Physics from the Australian National University in 1997, where he attended as a National Undergraduate Scholar. He spent several years as a software consultant prior to obtaining his PhD degree in simulation-based optimisation from Deakin University in 2004. He is currently a senior research academic and deputy director of the Centre for Intelligent Systems Research (CISR) at Deakin University.
- Bachelor of Science, Australian National University, 2001
- Bachelor of Engineering, Australian National University, 1997
- Doctor of Philosophy, Deakin University, 2004
2009 - present: Senior Research Fellow Centre for Intelligent Systems Research, Deakin
2004 - 2008: Research Fellow School of Engineering & IT (Research Priority Area)
2002 - 2004: Research Assistant School of Engineering, Deakin
1999 - 2002: PhD Researcher Ford Motor Company
1997 - 1999: Software Engineer Federal Parliament House, Canberra
1996 - 1997: Systems Engineer Department of Defence, Canberra
- Characterisation of industrial systems (complex, stochastic, dynamic)
- Event-based simulation modelling methodology and practice
- Data driven prediction and forecasting
- Robust optimisation, sequencing and scheduling
- Visualisation and haptics for decision support in complex environments
Emulation and intelligent control
Khosravi, A., Nahavandi, S., Creighton, D. "A Prediction Interval-Based Approach to Determine Optimal Structures of Neural Network Metamodels" Expert Systems with Applications, Vol. 37, No. 3, 2009, pp. 2377-2387. (Impact factor = 2.203, era Rank A*). Summary: A new prediction interval-based method is proposed in this paper for determining the optimal structure of neural networks. Neural networks selected using this method generate the highest quality prediction intervals.
Khosravi, A., Nahavandi, S. and Creighton, D. "A Lower Upper Bound Estimation Method for Construction of Neural Network-Based Prediction Intervals" IEEE Transactions on Neural Networks, Vol. 22, No. 3, 2011, pp. 337-346. (Impact factor = 2.952, era Rank A*). Summary: A new method is proposed for rapid construction of reliable prediction intervals. This method uses a neural network to estimate upper and lower bounds of prediction intervals.
Khosravi, A., Nahavandi, S., and Creighton, D. "Prediction Interval Construction and Optimization for Adaptive Neuro Fuzzy Inference", IEEE Transactions on Fuzzy Systems, Vol. 19, No. 5, 2011, pp. 983-988. (Impact factor = 4.26, era Rank A*). Summary: This paper discusses a novel method for construction of prediction intervals using adaptive neuro-fuzzy inference systems. It also proposes a novel method for optimising the quality of constructed prediction intervals.
Khosravi, A., Nahavandi, S. and Creighton, D. "Construction of Optimal Prediction Intervals for Load Forecasting Problems" IEEE Transactions on Power Systems, Vol. 25, No. 3, 2010, pp. 1496-1503. (Impact factor = 2.678, era Rank A*). Summary: This paper proposes a methodology for constructing optimal prediction intervals for uncertain outcomes of neural network models. Simulated annealing technique is used for minimising a prediction interval-based cost function.
Khosravi, A., Mazloumi, E., Nahavandi, S., Creighton, D., van Lint, J.W.C. "Prediction Intervals to Account for Uncertainties in Travel Time Prediction" IEEE Transactions on Intelligent Transportation Systems, Vol. 12, No. 2, 2011, pp.537-547. (Impact factor = 3.452, era Rank B) Rank 1 of 26 " JCR 2009 Subject category: Transportation Science & Tech.). Summary: Prediction intervals are constructed using the delta and Bayesian techniques for travel time estimation of urban buses and highway vehicles. Results show that intervals are more informative than point predictions.
Gu, N., Creighton, D., Nahavandi, S. "Selecting Optimal Norm and Step Size of Generalised Constant Modulus Algorithms under Non-Stationary Environments" Electronics Letters, Vol. 46, No. 25, 2010, pp. 1673-1674. (Impact factor = 0.965, era Rank A). Summary: An optimal norm and step size, for generalised constant modulus algorithms based on the norm of complex variables, was introduced. Superior performance was demonstrated for non-stationary environments.
Hossny, M., Nahavandi, S. and Creighton, D. "Comments on 'Information Measure for Performance of Image Fusion'" Electronics Letters, Vol. 44, No. 18, 2008, pp. 1066-1067. (Impact factor = 0.965, era Rank A). Summary: This paper discusses the problem of applying mutual information (MI) in assessing image fusion performance. It analytically suggests the use of other MI variations available in information theory literature.
Johnstone, M., Creighton, D. and Nahavandi, S. "Status - based Routing in Baggage Handling Systems: Searching verses Learning" IEEE Transactions on Systems, Man and Cybernetics: Part C, Vol. 40, No. 2, 2010, pp. 189-200. (Impact factor = 2.009, era Rank B). Summary: Intelligent control of baggage handling systems, while often suggested, is rarely investigated. This paper demonstrates agent's ability to learn a robust routing strategy based on bag status.