My Expertise
Eye activity computing, Task load estimation, Machine learning application, Computational Modelling, Image processing, Multimodal processing.
Keywords
SEO tags
Biography
Dr Siyuan Chen is a researcher in the School of Electrical Engineering and Telecommunications at UNSW Sydney. She obtained her PhD degree in Electrical Engineering from UNSW Sydney, worked as a Research Intern at NII Tokyo, Research Fellow in the School of Computing and Information Systems at the University of Melbourne, Visiting Scientist at INRIA, France, then joined UNSW Electrical Engineering and Telecommunications as a Research Fellow.
view more
Dr Siyuan Chen is a researcher in the School of Electrical Engineering and Telecommunications at UNSW Sydney. She obtained her PhD degree in Electrical Engineering from UNSW Sydney, worked as a Research Intern at NII Tokyo, Research Fellow in the School of Computing and Information Systems at the University of Melbourne, Visiting Scientist at INRIA, France, then joined UNSW Electrical Engineering and Telecommunications as a Research Fellow.
Her research lies at the intersection of artificial intelligence, machine learning, signal processing, affective computing and human-centred computing. She develops computational methods to understand human cognitive, emotional and behavioural states from multimodal physiological and behavioural signals, particularly eye activity, speech and head movement captured using wearable technologies.
Her long-term research vision is to develop multimodal wearable AI systems that can understand users continuously and unobtrusively in everyday environments, with applications in digital health, wellbeing and adaptive human–machine interaction. Her expertise spans machine learning, deep learning, computer vision, multimodal signal processing, wearable sensing and psychophysiology. Her research has attracted more than $1 million in competitive funding and has produced high-quality publications, patents and open research datasets.
Her current research expands these capabilities towards multimodal AI for digital health through interdisciplinary collaborations across Engineering, Psychology, Optometry and healthy ageing research. She welcomes students and collaborators interested in AI and machine learning, signal processing, affective computing, eye tracking, multimodal behavioural analysis, wearable sensing and digital health.
My Grants
$365K National Intelligence Post-Doctoral Grant (NIPG) Fellowship, 2024
$711K of US Army for the research on wearable multimodal behavioural signal modelling for longitudinal automatic task performing as joint CI, 2019
$23K Australia Endeavor Fellowship, 2015
My Qualifications
Ph.D. - Electrical Engineering (UNSW)
M.E. - Microelectronics (RMIT)
My Awards
2015, Australia Endeavor Fellowship
2013, NII Internship program, NII Tokyo
2012, The Commercialization Training Scheme Scholarship, UNSW
2011, The NICTA Postgraduate Award Scholarship
2011, The NICTA Research Project Award Scholarship, NICTA
My Research Activities
My research focuses on developing AI and machine learning methods for understanding human cognitive, emotional and behavioural states from multimodal physiological and behavioural signals.
I have particular expertise in eye behaviour computing, where I develop computer vision, signal processing and machine learning approaches to extract and model information from eye activity captured by head-mounted devices.
My research extends to multimodal AI, integrating eye activity with speech, head movement and other sensing modalities to develop more robust and interpretable representations of human states and performance.
Current research is expanding towards multimodal wearable AI for digital health, including the identification of behavioural and physiological markers associated with cognitive functioning, ageing and mental health, through interdisciplinary collaborations across Engineering, Psychology, Optometry and healthy ageing research. My long-term goal is to develop intelligent wearable and adaptive systems that can continuously and unobtrusively understand users in everyday environments, enabling applications in health monitoring, wellbeing and adaptive human–machine interaction.
Research interests: Artificial Intelligence and Machine Learning · Signal Processing · Multimodal AI · Affective Computing · Eye Tracking and Eye Behaviour Computing · Computer Vision · Wearable Sensing · Human-Centred Computing · Psychophysiology · Digital health · AI in clinical applications
My Research Supervision
Areas of supervision
I welcome Honours, Master's and PhD students interested in research at the intersection of artificial intelligence, machine learning, signal processing and human-centred computing. My projects typically involve developing computational methods to analyse physiological and behavioural signals and using these signals to understand human cognitive, emotional and behavioural states.
Potential areas of supervision include:
-Artificial intelligence and machine learning for physiological and behavioural signal analysis
-Multimodal AI and multimodal learning, including modelling and fusion of eye activity, speech, head movement and other sensor data
-Affective computing and human-state recognition, including cognitive load, emotion, activities and task transitions
-Eye tracking and eye behaviour computing, including eye-image analysis, pupil and eyelid modelling, gaze-related behaviours and wearable eye tracking
-Computer vision and deep learning for human-centred and wearable sensing applications
-Signal processing and representation learning for physiological and behavioural time-series data
-Wearable sensing and intelligent adaptive systems for continuous, unobtrusive monitoring in real-world environments
-AI for digital health and wellbeing, including behavioural and physiological markers associated with cognitive functioning, ageing and mental health
-Human-centred AI and human–computer interaction, particularly intelligent systems that adapt to users' cognitive and behavioural states
Projects can range from fundamental algorithm and machine-learning development to experimental studies and interdisciplinary applications. Depending on the project, students may gain experience in machine learning, deep learning, signal processing, computer vision, multimodal data analysis, experimental design, human-participant studies and wearable sensing. I particularly welcome students interested in combining rigorous engineering and AI methods with real-world problems in healthcare, wellbeing and human–machine interaction.
My Engagement
My engagement activities focus on building interdisciplinary and international research communities, translating research into practice, supporting colleagues and students, and promoting broader participation in engineering. I actively collaborate with researchers, clinicians and industry partners across Engineering, Psychology, Optometry and health-related disciplines, as well as with international research organisations, to connect advances in artificial intelligence and wearable sensing with real-world needs and applications.
I contribute actively to the international research community. I have served on the committee of the International Society of Clinical Eye Tracking (ISCET), contributed to major international conferences, including serving as Publication Co-Chair for INTERSPEECH 2026 and Social Media Co-Chair for ICMI 2026, and have organised invited tutorials and a journal special issue in my research field.
Research translation and external engagement are also important components of my work. I have engaged with industry partners to explore the translation of AI and behavioural sensing research into healthcare applications, contributed to patent development and commercialisation activities. These experiences help connect fundamental research with practical needs and create opportunities for interdisciplinary and industry collaboration.
I welcome opportunities to connect with researchers, clinicians, industry partners and other organisations interested in AI, multimodal sensing, wearable technologies and digital health. Please feel free to contact me to discuss potential research collaborations, interdisciplinary projects, research translation or other opportunities.
My Teaching
My teaching philosophy is centred on engaging, challenging and inspiring students to become independent learners and capable engineers. I believe students learn most effectively when they actively apply theoretical knowledge to authentic engineering problems, critically evaluate existing solutions, collaborate with others, and develop their own ideas. My role as an educator is therefore not only to explain technical concepts, but also to create an environment in which students are encouraged to question, explore, experiment and learn from both successes and failures.
I teach across undergraduate and postgraduate Electrical Engineering programs, with experience in circuits and signals, signal processing, engineering design, capstone projects, and engineering ethics. My teaching connects engineering fundamentals with contemporary technologies and real-world applications. In project-based courses, I encourage students to investigate emerging methods, including machine learning and computer vision, and to develop solutions to open-ended engineering problems through independent learning, teamwork and critical analysis.
Ultimately, I aim to help students develop the curiosity, confidence, critical thinking and lifelong learning skills needed to address complex engineering challenges and adapt to a rapidly changing technological landscape.
Lectured and tutored courses:
-First year: Engineering Design and Innovation course (ENGG1000) and Electrical Engineering course (ELEC1111)
-Second year: Circuits and Signals course (ELEC2134) and Modelling and Simulation course (ELEC2146)
-Third year: Signal Processing course (ELEC3104)
-Fourth year: Strategic Leadership and Ethics course (ELEC4622)
-Postgraduate: Electrical Engineering Capstone Course (ELEC9773) and Strategic Leadership and Ethics course (GSOE9510)
Publications
ORCID as entered in ROS
https://orcid.org/0000-0003-0272-5841
Related Links
