Associate Professor Oliver Obst

Associate Professor Oliver Obst

Associate Professor in Data Science,
Data Science


Dr Oliver Obst is Associate Professor in Data Science at Western Sydney University, in Parramatta, Sydney, Australia. Previously, he was team leader of the Data Mining Team at CSIRO (Data61), where he worked from Aug 2007 to Jan 2016, a lecturer at the University of Newcastle (2006/07), and a Post-doc at the University of Bremen, Germany (2006). He received a PhD in Artificial Intelligence (2006), and a Masters Degree in Computer Science from the University of Koblenz-Landau, in Koblenz, Germany.

This information has been contributed by Associate Professor Obst.


  • PhD University of Koblenz Landau


  • Artificial intelligence (AI)
  • Information Theory
  • Machine Learning
  • Neural Networks

Organisational Unit (School / Division)

  • Data Science


Phone: (02) 9685 9429
Location: EN.1.34

PLEASE NOTE: obtaining information from this Directory must be for the legitimate purposes of doing business with and within Western Sydney University, and must not be used for unsolicited bulk e-mailing (spamming) or similar purposes.


Previous Teaching Areas

  • 200411 Advanced Topics in Mathematics, 2017
  • 301034 Predictive Modelling, 2016
  • 301034 Predictive Modelling, 2017
  • 301117 Predictive Analytics, 2016
  • 301117 Predictive Analytics, 2017
  • 301119 Advanced Machine Learning, 2017
  • 301119 Advanced Machine Learning, 2018
  • 301119 Advanced Machine Learning, 2019
  • 301176 Advanced Mathematical Investigations, 2019
  • INFO7001 Advanced Machine Learning, 2022
  • MATH3011 Probabilistic Models and Inference, 2023
  • MATH7017 Probabilistic Graphical Models, 2022
  • MATH7017 Probabilistic Graphical Models, 2023



  • Alami, R., Biswas, J., Cakmak, M. and Obst, O. (2022), 'RoboCup 2021: Robot World Cup XXIV', : Springer 9783030986810.
  • Akiyama, H., Obst, O., Sammut, C. and Tonidandel, F. (2018), 'RoboCup 2017: Robot World Cup XXI', : Springer 9783030003074.

Chapters in Books

  • Obst, O. and Boedecker, J. (2014), 'Guided self-organization of input-driven recurrent neural networks', Guided Self-Organization: Inception, Springer 9783642537332.
  • Jurdak, R., Wang, X., Obst, O. and Valencia, P. (2011), 'Wireless sensor network anomalies : diagnosis and detection strategies', Intelligence-Based Systems Engineering, Springer 9783642179303.
  • Dylla, F., Ferrein, A., Lakemeyer, G., Murray, J., Obst, O., Rofer, T., Schiffer, S., Stolzenburg, F., Visser, U. and Wagner, T. (2008), 'Approaching a formal soccer theory from behaviour specifications in robotic soccer', Computers in Sport, WIT Press 9781845640644.

Journal Articles

  • Weigend, F., Clarke, D., Obst, O. and Siegler, J. (2023), 'A hydraulic model outperforms work-balance models for predicting recovery kinetics from intermittent exercise', Annals of Operations Research, vol 325, no 1 , pp 589 - 613.
  • Kaur, R., Ginige, J. and Obst, O. (2023), 'AI-based ICD coding and classification approaches using discharge summaries : a systematic literature review', Expert Systems with Applications, vol 213, no Pt. B .
  • Cliff, O., Lizier, J., Wang, X., Wang, P., Obst, O. and Prokopenko, M. (2017), 'Quantifying long-range interactions and coherent structure in multi-agent dynamics', Artificial Life, vol 23, no 1 , pp 34 - 57.
  • Lagerstrom, R., Arzhaeva, Y., Szul, P., Obst, O., Power, R., Robinson, B. and Bednarz, T. (2016), 'Image classification to support emergency situation awareness', Frontiers in Robotics and AI, vol 3 .
  • Prokopenko, M., Barnett, L., Harre, M., Lizier, J., Obst, O. and Wang, X. (2015), 'Fisher transfer entropy : quantifying the gain in transient sensitivity', Proceedings of the Royal Society of London. Series A : Mathematical, Physical and Engineering Sciences, vol 471, no 2184 .
  • Budden, D., Wang, P., Obst, O. and Prokopenko, M. (2015), 'RoboCup simulation leagues : enabling replicable and robust investigation of complex robotic systems', IEEE Robotics and Automation Magazine, vol 22, no 3 , pp 140 - 146.
  • Obst, O. (2014), 'Distributed fault detection in sensor networks using a recurrent neural network', Neural Processing Letters, vol 40, no 3 , pp 261 - 273.
  • Zeman, A., Obst, O. and Brooks, K. (2014), 'Complex cells decrease errors for the Muller-Lyer illusion in a model of the visual ventral stream', Frontiers in Computational Neuroscience, vol 8 .
  • Zeman, A., Obst, O., Brooks, K. and Rich, A. (2013), 'The Muller-Lyer illusion in a computational model of biological object recognition', PLoS One, vol 8, no 2 .
  • Obst, O., Trinchi, A., Hardin, S., Chadwick, M., Cole, I., Muster, T., Hoschke, N., Ostry, D., Price, D., Pham, K. and Wark, T. (2013), 'Nano-scale reservoir computing', Nano Communication Networks, vol 4, no 4 , pp 189 - 196.
  • Boedecker, J., Obst, O., Lizier, J., Mayer, N. and Asada, M. (2012), 'Information processing in echo state networks at the edge of chaos', Theory in Biosciences, vol 131, no 3 , pp 205 - 213.
  • Prokopenko, M., Lizier, J., Obst, O. and Wang, X. (2011), 'Relating Fisher information to order parameters', Physical Review E (Statistical, Nonlinear, and Soft Matter Physics), vol 84, no 4 .
  • Prokopenko, M., Ay, N., Obst, O. and Polani, D. (2010), 'Phase transitions in least-effort communications', Journal of Statistical Mechanics: Theory and Experiment, vol 2010, no 11 .
  • Boedecker, J., Obst, O., Mayer, N. and Asada, M. (2009), 'Initialization and self-organized optimization of recurrent neural network connectivity', HFSP Journal, vol 3, no 5 , pp 340 - 349.

Conference Papers

  • Sharma, S., Fang, G., Chen, Z., Obst, O., Tissue, D., Zou, J. and Liang, W. (2023), 'Capsicum flower identification for robotic pollination in greenhouses', International Conference on Machine Learning and Cybernetics, Adelaide, S.A..
  • Mayer, N. and Obst, O. (2022), 'Analyzing echo-state networks using fractal dimension', International Joint Conference on Neural Networks , Padua, Italy.
  • Weigend, F., Siegler, J. and Obst, O. (2021), 'A new pathway to approximate energy expenditure and recovery of an athlete', Genetic and Evolutionary Computation Conference, Lille, France.
  • Michael, O., Obst, O., Schmidsberger, F. and Stolzenburg, F. (2019), 'RoboCupSimData : software and data for machine learning from RoboCup Simulation League', RoboCup (Conference), Montreal, Canada.
  • Michael, O., Obst, O., Schmidsberger, F. and Stolzenburg, F. (2018), 'Analysing soccer games with clustering and conceptors', RoboCup (Conference), Nagoya, Japan.
  • Nakashima, T., Mifune, S., Henrio, J., Obst, O., Wang, P. and Prokopenko, M. (2015), 'Kick extraction for reducing uncertainty in RoboCup logs', International Conference on Human-Computer Interaction, Los Angeles, Calif..
  • Budden, D., Wang, P., Obst, O. and Prokopenko, M. (2015), 'Simulation leagues : analysis of competition formats', RoboCup (Conference), Joao Pessoa, Brazil.
  • Cliff, O., Lizier, J., Wang, X., Wang, P., Obst, O. and Prokopenko, M. (2014), 'Towards quantifying interaction networks in a football match', RoboCup International Symposium, Eindhoven, Netherlands.
  • Hartmann, C., Boedecker, J., Obst, O., Ikemoto, S. and Asada, M. (2013), 'Real-time inverse dynamics learning for musculoskeletal robots based on echo state Gaussian process regression', Robotics: Science and Systems Conference , Sydney, N.S.W..
  • Obst, O. and Riedmiller, M. (2012), 'Taming the reservoir : feedforward training for recurrent neural networks', International Joint Conference on Neural Networks, Brisbane, Qld..
  • Obst, O., Polani, D. and Prokopenko, M. (2011), 'Origins of scaling in genetic code', European Conference on Artificial Life, Budapest, Hungary.
  • Mayer, N., Obst, O. and Yu-Chen, C. (2010), 'Time series causality inference using echo state networks', LVA/ICA, St. Malo, France.
  • Obst, O., Boedecker, J. and Asada, M. (2010), 'Improving recurrent neural network performance using transfer entropy', International Conference on Neural Information Processing, Sydney, N.S.W..
  • Boedecker, J., Obst, O., Mayer, N. and Asada, M. (2009), 'Studies on reservoir initialization and dynamics shaping in echo state networks', European Symposium on Artificial Neural Networks, Bruges, Belgium.
  • Wang, X., Lizier, J., Obst, O., Prokopenko, M. and Wang, P. (2008), 'Spatiotemporal anomaly detection in gas monitoring sensor networks', EWSN (Conference), Bologna, Italy.
  • Obst, O., Wang, X. and Prokopenko, M. (2008), 'Using echo state networks for anomaly detection in underground coal mines', IPSN (Conference), St. Louis, Mo..

Dr Oliver Obst is a researcher with a background in machine learning and intelligent decision-making. His research interests and projects span fundamental research in machine learning, environmental sensing, robotics, and language processing for health applications. Oliver is currently leading the machine learning effort for a larger environmental sensing project (SiMPACT). He is leader of a WSU initiative on Assisted Living -- sensor-enabled smart homes and robotics. He is also working on a robotics project for plant pollination in horticulture, and exploring the use of language models for clinical coding applications. His research contributes to theory and applications of recurrent and deep neural networks, learning of representations, reinforcement learning, and information theory. He has experience in finding patterns in data, selecting informative features, and decision-making in autonomous agents for various applications, including smart electrical energy, minerals mining, environmental monitoring, intelligent materials, robotics, big data in astronomy, cybersecurity, and health. Oliver is also interested in walking and mobile robots in all aspects from design and manufacturing to control and actuation.

This information has been contributed by Associate Professor Obst.

Current Projects

Title: Smart Irrigation Management for Parks and Cool Towns (SIMPaCT)
  • Department of Planning and Environment
  • Department of Planning and Environment
  • Sydney Water Corporation
Western Researchers: Sebastian Pfautsch, Oliver Obst, Bahman Javadi Jahantigh and Nicky Morrison
Years: 2021-12-01 - 2024-07-31
ID: P00027609

Previous Projects

Title: Deep Conceptors for Temporal Data Mining
  • University of Western Sydney
  • German Academic Exchange Service (DAAD)
Western Researchers: Oliver Obst
Years: 2017-01-01 - 2018-12-31
ID: P00023581
Title: Capital Markets CRC (CMCRC) PhD Scholarship - Geoffrey Cheng Kang Chang - Developing a Predictive Model for Credit Demand using Machine Learning and Big Data Models
  • RoZetta Institute Limited
Western Researchers: Kathy Tannous and Oliver Obst
Years: 2017-05-01 - 2021-06-30
ID: P00024161
Title: Fraud detection for financial products
  • RoZetta Institute Limited
Western Researchers: Oliver Obst and Kathy Tannous
Years: 2018-02-19 - 2019-05-23
ID: P00024928


Current Supervision

Thesis Title: Fraud Detection for Financial Products.
Field of Research:
Thesis Title: Analogising Style Transfer for Author Document Attribution
Field of Research:
Thesis Title: Achieving High Mean Accuracy with Semi-Supervised Learning using Small Number of Labeled Observations
Field of Research:
Thesis Title: Distributed Knowledge based Clinical Auto-Coding System
Field of Research:
Thesis Title: Developing a Predictive Model for Credit Demand using Machine Learning and Big Data Models
Field of Research:
Thesis Title: Mapping Clinical Classification Systems with Natural Language Processing & Machine Learning
Field of Research:
Thesis Title: An investigation of efficient and effective real-time object tracking and recognition
Field of Research:

Previous Supervision

Thesis Title: A Generalised Hydraulic Performance Model For Intermittent Exercise
Field of Research:

Western Sydney University

Locked Bag 1797
Penrith NSW 2751

ABN 53 014 069 881
CRICOS Provider No: 00917k