Dr Aaron Wong
Office PVC - Engineering and Built Environment (Computer Science and Software Engineering)
- Phone:(02) 49854324
From computer science to neuroimaging
Dr Aaron Wong was initially spurred into the world of computing science thanks to the foresight of his parents – who enrolled him into coding workshops when he was just seven years old. Today, his interdisciplinary research journey is motivated instead by a love of learning and collaboration.
Although Aaron dabbled in a number of extra-curricular activities throughout his primary years, including attempting to learn Chinese, coding was the one that stuck. Aaron admits that his Chinese language skills may have suffered as a consequence: “My accent is terrible,” he confides
But although the lack of language skills may have disappointed his RoboCup team-mates at the 2008 World Championship in Suzhou, China, the NUbots couldn’t have had too much to complain about when Aaron’s well-refined coding practise helped launched them to global victory.
NUbots are autonomous, football-playing robots who compete across the globe in soccer matches. While they seem like just a cute bit of fun, the aim of RoboCup and the footy-playing robots is to combine artificial intelligence and robotics to develop solutions in the broader AI and robotics fields.
Although most students get involved with the NUbots projects within the Newcastle Robotics Laboratory, led by Associate Professor Stephan Chalup, as part of coursework or summer scholarship programs, Aaron was invited onto the team because of his natural programming flair.
He had been enrolled in a double degree in Computer Science and Computer Engineering at UON– a career choice which had been a long time in the making.
“I always knew I wanted to do something in the field of computing - I had a knack for programing because I started really young.
“I was interested in the foundations of mathematics, so coding was just the way that I applied that skill set - I found it easy and I took off with it.”
Once Aaron progressed to high school, he became fascinated instead with computing hardware. He began fixing computers for fun when he was just eleven years old – a hobby which he explains was merely a consequence of the natural progression of his interests.
Of robots and rescues
Throughout his undergraduate studies, Aaron become engrossed in the field of artificial intelligence (AI), and continued in his machine learning research throughout his Honours and PhD projects.
“I started off programming a rescue robot to compete in the RoboCup Federation – it was an autonomously driving wheeled robot designed to find victims in a disaster scenario.
“I concentrated on sound recognition and localisation. Because the robot was so low to the ground, sound was pretty much the only way of finding people.”
From there, Aaron moved on to acoustic and image processing for his PhD. Then, through a roundabout series of research questions and aims, he found himself specialising in the unusual task of teaching of emotions to robots.
“We were combining together all the sensory and effective processing.
“So we’d pull out all the visual features we were interested in - like colour, fractal dimension and facial perception (paredolia) – then feed that into a learning algorithm to get the robot to learn by itself via user feedback.”
When Aaron was offered a part time technical support position within Associate Professor Frini Karayanidis’ Functional Neuroimaging Laboratory, his new working environment saw this emotional learning aspect truly came into focus.
“There was definitely an overlap – and it helped me with my writing too, that I was able to concentrate on the biological and psychological perspective of the project.
“That general integration of sensory input which is basically what our brain does. We don’t know exactly what happens there but we’ve got lots of bits of ideas.
“What I could then do was build those ideas into my engineering project.”
Combining collaboration with innovation
Since finishing his PhD, Aaron has moved on to work with a number of research groups from across the University, including with the team at his old PhD stomping ground, the Functional Neuroimaging Laboratory.
“I’m really open to collaboration – I’m flexible and have found I can work with just about everyone.”
At the moment, Aaron is involved with UON’s PRC for Stroke and Brain Imaging’s streamlining of patient assessment techniques. They are hoping to minimise the need for number of pricey MRI scans performed in the clinic.
“To infer brain function from MRI costs much more and takes a lot longer, when compared with an EEG.”
By building a model which feeds EEG and MRI data together, patterns between the two types of data can be used to predict MRI results from EEG scans.
“The project is a massive data mining process - but it should eventually save clinics a lot of time and money.”
STEM outreach solutions
Aware of the difference an early start can make to a child’s attitudes to science and learning, Aaron is now invested in primary school workshops much like the ones he benefited from as a child.
Aaron initiated UON’s RoboCup Junior project in 2011 when he was approached by a parent at a RoboCup event.
“He was really keen to start something like what we were doing but for younger kids.
“It’s good for them to be able to see the practical applications of engineering from an early age, and to realise it’s all about having a go.”
“It’s that iterative learning process - writing one line of code and sending it out to the robot. Then asking – ‘Does it move, does it not? Did I do something wrong, did I do something right?’
“You can assess that step by step, and that's the kind of logical thinking that you need to be an engineer. You need that ability to break down your jobs into tiny little steps so you can go ‘Tick, tick, tick!’ - also it builds your confidence as well.”
Dr Aaron S.W. Wong research and interests lay in the interdisciplinary fields of computer science, robotics, cognitive neuroscience, psychology, biofeedback and built environment; Anthropocentric bio-cybernetic computing, mainly implementing sensory perception and affect for humanoid robots using learning, with a focus on manifold learning for the built environment.
His accomplishments include World SPL Champion, RoboCup, 2008-Soccer Robots, and Environmental Affective Robotics.
Currently employed as a technical research assistant in the Priority Research Center for Stroke and Brain Injury (PRC-SBI). Working on a combination of core projects relating to the PRC-SBI Psychological Processes Hub, which include software development of processing pipelines for Magnetic Resonance Imaging processing (MRI) mainly on Diffusion Weighted Imaging (DWI), and Electroencephalogram (EEG) which includes development and maintenance of software processing pipelines for evoked response potentials, time-frequency analysis and network connectivity. In addition to conducting research into applications of Multivariate Joint Modelling, using Hierarchical Bayesian Models for the AGE-ility Project.
- Doctor of Philosophy, University of Newcastle
- Bachelor of Engineering (Computer Eng)(Honours), University of Newcastle
- Bachelor of Computer Science, University of Newcastle
- Artifical Intelligence
- Computational Neuroscience
- English (Fluent)
- Cantonese (Working)
Fields of Research
|170203||Knowledge Representation and Machine Learning||50|
|080199||Artificial Intelligence and Image Processing not elsewhere classified||25|
|170205||Neurocognitive Patterns and Neural Networks||25|
|Dates||Title||Organisation / Department|
Technical Research Assistant - Software/Hardware Development and Maintainance
Software Development and Maintainance:
- EEG Processing Pipelines: Evoked response potentials, time-frequency analysis, and network connectivity.
|Priority Research Centre for Stroke and Brain Injury
Global Leader of Innovation 2014, UON
The University of Newcastle
RoboCup Australian Open Champion 2011 - NUbots
RoboCup International World Champion SPL 2008 - NUmanoids
Best Student Paper: 46th Annual Conference of the Archtectural Science Association
Australian and New Zealand Architectural Science Association (ANZAScA)
|Year||Title / Rationale|
Medical Software Industry Association
Social Robotics: Implications to Healthcare
For publications that are currently unpublished or in-press, details are shown in italics.
Journal article (6 outputs)
Wong ASW, Cooper PS, Conley AC, McKewen M, Fulham WR, Michie PT, Karayanidis F, 'Event-related potential responses to task switching are sensitive to choice of spatial filter', Frontiers in Neuroscience, 12 (2018)
© 2018 Wong, Cooper, Conley, McKewen, Fulham, Michie and Karayanidis. Event-related potential (ERP) studies using the task-switching paradigm show that multiple ERP components are... [more]
© 2018 Wong, Cooper, Conley, McKewen, Fulham, Michie and Karayanidis. Event-related potential (ERP) studies using the task-switching paradigm show that multiple ERP components are modulated by activation of proactive control processes involved in preparing to repeat or switch task and reactive control processes involved in implementation of the current or new task. Our understanding of the functional significance of these ERP components has been hampered by variability in their robustness, as well as their temporal and scalp distribution across studies. The aim of this study is to examine the effect of choice of reference electrode or spatial filter on the number, timing and scalp distribution of ERP elicited during task-switching. We compared four configurations, including the two most common (i.e., average mastoid reference and common average reference) and two novel ones that aim to reduce volume conduction (i.e., reference electrode standardization technique (REST) and surface Laplacian) on mixing cost and switch cost effects in cue-locked and target-locked ERP waveforms in 201 healthy participants. All four spatial filters showed the same well-characterized ERP components that are typically seen in task-switching paradigms: the cue-locked switch positivity and target-locked N2/P3 effect. However, both the number of ERP effects associated with mixing and switch cost, and their temporal and spatial resolution were greater with the surface Laplacian transformation which revealed rapid temporal adjustments that were not identifiable with other spatial filters. We conclude that the surface Laplacian transformation may be more suited to characterize EEG signatures of complex spatiotemporal networks involved in cognitive control.
Cooper PS, Wong ASW, McKewen M, Michie PT, Karayanidis F, 'Frontoparietal theta oscillations during proactive control are associated with goal-updating and reduced behavioral variability', Biological Psychology, 129 253-264 (2017) [C1]
© 2017 Low frequency oscillations in the theta range (4¿8 Hz) are increasingly recognized as having a crucial role in flexible cognition. Such evidence is typically derived from s... [more]
© 2017 Low frequency oscillations in the theta range (4¿8 Hz) are increasingly recognized as having a crucial role in flexible cognition. Such evidence is typically derived from studies in the context of reactive (stimulus-driven) control processes. However, little research has explored the role of theta oscillations in preparatory control processes. In the current study, we explored the extent of theta oscillations during proactive cognitive control and determined if these oscillations were associated with behavior. Results supported a general role of theta oscillations during proactive cognitive control, with increased power and phase coherence during the preparatory cue interval. Further, theta oscillations across frontoparietal electrodes were also modulated by proactive control demands, with increased theta phase synchrony and power for cues signaling the need for goal updating. Finally, we present novel evidence of negative associations between behavioral variability and both power and phase synchrony across many of these frontoparietal electrodes that were associated with the need for goal updating. In particular, greater consistency in frontoparietal theta oscillations, indicated by increased theta phase and power during mixed-task blocks, resulted in mor e consistent task-switching performance. Together, these findings provide new insight into the temporal dynamics and functional relevance of theta oscillations during proactive cognitive control.
Karayanidis F, Keuken MC, Wong A, Rennie JL, de Hollander G, Cooper PS, et al., 'The Age-ility Project (Phase 1): Structural and functional imaging and electrophysiological data repository', NeuroImage, 124 1137-1142 (2016) [C1]
© 2015 Published by Elsevier Inc. Our understanding of the complex interplay between structural and functional organisation of brain networks is being advanced by the development ... [more]
© 2015 Published by Elsevier Inc. Our understanding of the complex interplay between structural and functional organisation of brain networks is being advanced by the development of novel multi-modal analyses approaches. The Age-ility Project (Phase 1) data repository offers open access to structural MRI, diffusion MRI, and resting-state fMRI scans, as well as resting-state EEG recorded from the same community participants (n = 131, 15-35 y, 66 male). Raw imaging and electrophysiological data as well as essential demographics are made available via the NITRC website. All data have been reviewed for artifacts using a rigorous quality control protocol and detailed case notes are provided.
Cooper PS, Wong ASW, Fulham WR, Thienel R, Mansfield E, Michie PT, Karayanidis F, 'Theta frontoparietal connectivity associated with proactive and reactive cognitive control processes', NeuroImage, 108 354-363 (2015) [C1]
© 2015 Elsevier Inc. Cognitive control involves both proactive and reactive processes. Paradigms that rely on reactive control have shown that frontoparietal oscillatory synchroni... [more]
© 2015 Elsevier Inc. Cognitive control involves both proactive and reactive processes. Paradigms that rely on reactive control have shown that frontoparietal oscillatory synchronization in the theta frequency band is associated with interference control. This study examines whether proactive control is also associated with connectivity in the same frontoparietal theta network or involves a distinct neural signature. A task-switching paradigm was used to differentiate between proactive and reactive control processes, involved in preparing to switch or repeat a task and resolving post-target interference, respectively. We confirm that reactive control is associated with frontoparietal theta connectivity. Importantly, we show that proactive control is also associated with theta band oscillatory synchronization but in a different frontoparietal network. These findings support the existence of distinct proactive and reactive cognitive control processes that activate different theta frontoparietal oscillatory networks.
Boecking B, Chalup SK, Seese D, Wong ASW, 'Support vector clustering of time series data with alignment kernels', Pattern Recognition Letters, 45 129-135 (2014) [C1]
Time series clustering is an important data mining topic and a challenging task due to the sequences' potentially very complex structures. In the present study we experimenta... [more]
Time series clustering is an important data mining topic and a challenging task due to the sequences' potentially very complex structures. In the present study we experimentally investigate the combination of support vector clustering with a triangular alignment kernel by evaluating it on an artificial time series benchmark dataset. The experiments lead to meaningful segmentations of the data, thereby providing an example that clustering time series with specific kernels is possible without pre-processing of the data. We compare our approach and the results and learn that the clustering quality is competitive when compared to other approaches. © 2014 Published by Elsevier B.V.
Wong AS, Chalup SK, Bhatia S, Jalalian A, Kulk JA, Nicklin SP, Ostwald M, 'Visual gaze analysis of robotic pedestrians moving in urban space', Architectural Science Review, 55 213-223 (2012) [C1]
|Show 3 more journal articles|
Conference (7 outputs)
Harms L, Zavitsanou K, Meehan C, Wong A, Fullham R, Todd J, et al., 'Examination of mismatch negativity, oscillatory activity and related neurochemistry in a developmental rat model of Schizophrenia', JOURNAL OF NEUROCHEMISTRY, Cairns, AUSTRALIA (2015) [E3]
Karayanidis F, Cooper PS, Wong AS, Hunter M, Rennie J, Fulham WR, Michie PT, 'MIDFRONTAL THETA TO GOAL UNCERTAINTY: VARIABILITY RELATED TO INDIVIDUAL DIFFERENCES IN ANXIETY AND COGNITIVE CONTROL EFFICIENCY', PSYCHOPHYSIOLOGY, Seattle, WA (2015) [E3]
Wong ASW, Nicklin S, Hong K, Chalup SK, Walla P, 'Robot emotions generated and modulated by visual features of the environment', IEEE Symposium on Computational Intelligence for Creativity and Affective Computing (CICAC), Singapore, SINGAPORE (2013) [E1]
Wong AS, Chalup SK, Bhatia S, Jalalian A, Kulk JA, Ostwald M, 'Humanoid robots for modelling and analysing visual gaze dynamics of pedestrians moving in urban space', Conference Proceedings 45th Annual Conference of the Australian and New Zealand Architectural Science Association, Sydney, NSW (2011) [E1]
Wong AS, Chalup SK, 'Towards visualisation of sound-scapes through dimensionality reduction', IEEE International Joint Conference on Neural Networks, 2008 Proceedings, Hong Kong (2008) [E1]
Henderson N, Nicklin SP, Wong AS, Kulk JA, Chalup SK, King R, et al., 'The 2008 NUManoids Team Report', RoboCup. Participating Teams 2008. Downloads, Suzhou, China (2008) [E2]
Wong AS, Chalup SK, 'Sound-scapes for robot localisation through dimensionality reduction', Proceedings of the 2008 Australasian Conference on Robotics & Automation, Canberra, ACT (2008) [E1]
|Show 4 more conferences|
Grants and Funding
|Number of grants||2|
Click on a grant title below to expand the full details for that specific grant.
20181 grants / $20,000
How transient is a transient ischemic attack (TIA)? Frontal-network profiles as indices of sustained cognitive impairment post-TIA$20,000
Funding body: Hunter Medical Research Institute
|Funding body||Hunter Medical Research Institute|
|Project Team||Professor Frini Karayanidis, Doctor Patrick Cooper, Doctor Aaron Wong, Doctor Andrew Bivard, Conjoint Professor Chris Levi|
|Type Of Funding||C3120 - Aust Philanthropy|
20161 grants / $4,500
Funding body: Keats Endowment Research Fund
Number of supervisions
Total current UON EFTSL
|Commenced||Level of Study||Research Title||Program||Supervisor Type|
|2018||PhD||Multimodal Emotion Recognition||PhD (Computer Science), Faculty of Engineering and Built Environment, The University of Newcastle||Co-Supervisor|
|2015||PhD||Development of a Brain Controlled Walking Assistant||PhD (Computer Science), Faculty of Engineering and Built Environment, The University of Newcastle||Co-Supervisor|
The map is a representation of a researchers co-authorship with collaborators across the globe. The map displays the number of publications against a country, where there is at least one co-author based in that country. Data is sourced from the University of Newcastle research publication management system (NURO) and may not fully represent the authors complete body of work.
|Country||Count of Publications|
Dr Aaron Wong
Functional Neuroimaging Laboratory Priority Research Centre for Stroke and Brain Injury
Office PVC - Engineering and Built Environment
Faculty of Engineering and Built Environment
Functional Neuroimaging Laboratory Priority Research Centre for Stroke and Brain Injury
School of Psychology
Faculty of Science
Computer Science and Software Engineering