Dr Stephanie Baker - Research Portfolio

JCU > Research Portfolio > Dr Stephanie Baker

About

Dr Steph Baker is a computer systems engineer with multidisciplinary research interests. Her main research interest is the use of artificial intelligence to solve significant problems in areas from healthcare to environmental science. Much of her research to date has focused on healthcare, which has allowed her to make significant contributions in health monitoring and prognostics assessment.

Steph holds a PhD in biomedical and software engineering. Her doctoral thesis was awarded the Dean's Award for Research Higher Degree Excellence. Steph also holds a Bachelor of Engineering (Computer Systems) with Class I Honours. She has taught at James Cook University since 2016, joining the Cairns team in early 2021.

Healthcare Research

Steph has undertaken substantial research in the intersection of healthcare and engineering. One of her key interests lies in enabling a higher standard of at-home and rural healthcare, which is vitally important in Northern Australia. Much of her research has focused on accurate measurement of health parameters using non-invasive and wearable technology. She is also interested in using machine learning for diagnosing illness and identifying likely outcomes to enable treatment decisions that are tailored to individual patients.

Other Research

Steph is also conducting research in the domain of responsible AI, which involves making AI systems transparent, fair, and accountable to human users. She is particularly interested in how AI decisions can be explained to end-users in a way that is interpretable and acceptable. Responsible AI has applications in many domains, including healthcare, autonomous vehicles, and generative AI systems such as ChatGPT.

Additionally, Steph is interested in the environmental sciences. She is currently researching machine learning methods for improving the image quality of remote sensing data. This research will lead to tools that will support environmental and climate science applications.

Teaching

Steph has taught a variety of engineering subjects for various year levels, including EG1002 Computers and Sensors, EG1012 Electric Circuits, EE2201 Electric Theory, EE2300 Electronics 1, EE3600 Automatic Control 1, EE4010 Analog Signals and Filters, and EG4011+EG4012 Thesis. Her teaching focuses on developing collaborative and engaging learning experiences that develop student's skills and confidence in the engineering context. Steph is also actively involved in supervising PhD candidates and undergraduate Honours projects.

Supervising

Steph is currently available to supervise PhD projects. If you are interested in a PhD in an area related to her research, then please contact her on stephanie.baker@jcu.edu.au with a CV, your research interests, and your previous research experience. Scholarships are available for PhD studies, but are highly competitive. Available projects are listed below, however Steph is happy to work with you to develop a new project in your area of interest:

Available Projects

The following project/s are currently available:

Machine learning for non-invasive vital sign measurement in premature babies

In this project, the successful candidate will work to develop methods for non-invasively measuring vital signs and other health parameters in the neonatal intensive care unit setting, using data collected from the Townsville University Hospital. This project would suit a candidate who is passionate about healthcare with a background in computer engineering, data science, or a related field. This project is running in collaboration with Dr Yoga Kandasamy (Senior Neonatologist, Townsville University Hospital).

Current Funding

The following projects are currently funded:

Northern Australia Regional Digital Health Collaborative (NARDHC)

Project title: Fusion of wearable and environmental sensors for remote monitoring of health and wellbeing in elderly populations.

Indicative funding: $48,063 over six months

Summary: This project aims to develop a smart home health monitoring prototype that improves upon existing technology by fusing information from multiple sensors. The proposed system will use non-invasive wearable sensors, non-contact mmWave technology, and artificial intelligence to monitor key vital signs, physical activity, stress, fatigue, and environmental conditions. The goal of this project is to prototype a comprehensive system for monitoring health and wellbeing in rural and remote Australia, with particular focus on elderly persons.

Investigators: Stephanie Baker, Euijoon Ahn, Tao (Kevin) Huang, Bronson Philippa, Caryn West, and Christopher Rouen.

--------------------------------------------------------------------------

Townsville Hospital and Health Service (THHS) Study, Education, and Research Trust Account (SERTA) Fund

Project title: No Pressure: A non-invasive and continuous machine learning method for measuring blood pressure in the neonatal intensive care unit

Indicative funding: $10,000 over 3 years

Summary: This project aims to develop machine learning algorithms capable of continuously monitoring blood pressure in babies born very preterm, using heart activity waveforms obtained from low-cost and non-invasive photoplethysmogram and electrocardiogram sensors. In current practice, blood pressure monitoring of preterm infants is performed using invasive arterial blood pressure monitoring, introducing significant risk of infection, thrombosis, and more to already vulnerable babies. It is expected that this work will provide a non-invasive alternative for measuring this key parameter, in turn leading to improved patient outcomes. This work also has significant potential to support critical care in low-resource and remote areas.

Investigators: Yoga Kandasamy, Stephanie Baker

--------------------------------------------------------------------------

Northern Australia Regional Digital Health Collaborative (NARDHC)

Project title: A mobile app and dashboard for effective management of early-stage chronic kidney disease

Indicative funding: $48,724 over six months

Summary: The incidence and prevalence of chronic kidney disease (CKD) varies globally, and people in the lowest socioeconomic quartile have a 60% higher risk of progressive CKD. This project aims to develop a mobile app that detects vulnerable individuals who are at risk of deterioration in renal function and are needing intervention, while also allowing monitoring and appropriate education to those who are progressing steadily. The expected outcome is a novel mobiele analytic app that can improve the management of CKD patients in rural and remote areas for better health outcomes and planning.

Investigators: Euijoon Ahn, Jason Holdsworth, Stephanie Baker, Konrad Kangru, Krishan Madhan

--------------------------------------------------------------------------

Teaching

EE2300: Electronics 1 (Level 2; CNS)
EE4010: Analog Signals and Filters (Level 4; CNS & TSV)
EG1002: Computing and Sensors (Level 1; CNS)
EG1012: Electric Circuits (Level 1; CNS)

Interests

Research

machine learning
healthcare
rural and remote healthcare
wearable sensors
non-invasive health monitoring
environmental sensing
remote sensing

Experience

2021 to present - Lecturer, James Cook University (Cairns)
2016 to 2021 - Various lecturing and tutoring roles, James Cook University (Townsville)

Research Disciplines

Socio-Economic Objectives

Honours

Awards

2022 - Dean's Award for Research Higher Degree Excellence
2022 - JCU Citation for Outstanding Contributions to Student Learning

Publications

These are the most recent publications associated with this author. To see a detailed profile of all publications stored at JCU, visit ResearchOnline@JCU. Hover over Altmetrics badges to see social impact.

Journal Articles

Baker S, Huang Z and Philippa B (2023) Lightweight Neural Network For Spatiotemporal Filling of Data Gaps in Sea Surface Temperature Images. IEEE Transactions on Geoscience and Remote Sensing, 61.
Baker S and Xiang W (2023) Artificial Intelligence of Things for Smarter Healthcare: A Survey of Advancements, Challenges, and Opportunities. IEEE Communications Surveys & Tutorials, 25 (2). pp. 1261-1293
Baker S and Kandasamy Y (2023) Machine learning for understanding and predicting neurodevelopmental outcomes in premature infants: a systematic review. Pediatric Research, 93. pp. 293-299
Charlton P, Allen J, Bailon R, Baker S, Behar J, Chen F, Clifford G, Clifton D, Davies H, Ding C, Ding X, Dunn J, Elgendi M, Ferdoushi M, Franklin D, Gil E, Hassan M, Hernesniemi J, Hu X, Ji N, Khan Y, Kontaxis S, Korhonen I, Kyriacou P, Laguna P, Lazaro J, Lee C, Levy J, Li Y, Liu C, Liu J, Lu L, Mandic D, Marozas V, Mejia-Mejia E, Mukkamala R, Nitzan M, Pereira T, Poon C, Ramella-Roman J, Saarinen H, Shandhi M, Shin H, Stansby G, Tamura T, Vehkaoja A, Wang W, Zhang Y, Zhao N, Zheng D and Zhu T (in press) The 2023 wearable photoplethysmography roadmap. Physiological Measurement,
Kandasamy Y and Baker S (2023) An Exploratory Review on the Potential of Artificial Intelligence for Early Detection of Acute Kidney Injury in Preterm Neonates. Diagnostics, 13 (18).
Baker S, Xiang W and Atkinson I (2022) A computationally efficient CNN-LSTM neural network for estimation of blood pressure from features of electrocardiogram and photoplethysmogram waveforms. Knowledge Based Systems, 250.
Baker S, Xiang W and Atkinson I (2021) A hybrid neural network for continuous and non-invasive estimation of blood pressure from raw electrocardiogram and photoplethysmogram waveforms. Computer Methods and Programs in Biomedicine, 207.
Baker S, Xiang W and Atkinson I (2021) Hybridized neural networks for non-invasive and continuous mortality risk assessment in neonates. Computers in Biology and Medicine, 134.
Baker S, Xiang W and Atkinson I (2021) Determining respiratory rate from photoplethysmogram and electrocardiogram signals using respiratory quality indices and neural networks. PLoS ONE, 16 (4).
Baker S, Xiang W and Atkinson I (2020) Continuous and automatic mortality risk prediction using vital signs in the intensive care unit: a hybrid neural network approach. Scientific Reports, 10.
Baker S, Xiang W and Atkinson I (2017) Internet of Things for smart healthcare: technologies, challenges, and opportunities. IEEE Access, 5. pp. 26521-26544

Collaboration

The map shows research collaborations by institution from the past 7 years.
Note: Map points are indicative of the countries or states that institutions are associated with.