JCU > Research Portfolio > Dr Kelly Trinh

About

My research focuses on Bayesian statistics, machine learning, dimension reduction techniques, and time-varying parameter models. I have a strong interest in developing methodology statistical analysis and machine learning algorithms in applied research areas.

Methodology research:

- Bayesian time series analysis

- Machine learning and neural network in time series

- High dimensional modelling

- Modelling uncertainties

- Spatial analysis and point pattern analysis

Applied research

- Macroeconomic (forecasting and understanding impacts of economic uncertainities, policies on an economy)

- Economic Health

- Economic geography

- Health application

Grants:

- "Emergency departmnet waiting time prediction in real-time" funded by the Emergency Medicine Foundation, $36,733 https://emergencyfoundation.org.au/projects/emergency-department-waiting-time-predictions-in-real-time/

Teaching

MA2405: Advanced Statistical Modelling (Level 2; CNS & TSV)

Interests

Research

Bayesian statistics
Dimension reduction techniques
State Space Models
Time-series
Forecasting
Machine learning algorithms
Bioinformatics
Macroeconomics

Experience

2017 to 2019 - Data Scientist, Data61,CSIRO (Brisbane)

Research Disciplines

Socio-Economic Objectives

Honours

Awards

2013 to 2017 - UQ Scholarship for Post Graduate Students
2013 to 2014 - Distinguished Teaching Awards
2011 to 2012 - UQ Summer Research Scholarship
2009 to 2011 - UQ Scholarship for Undergraduate Students

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

Vos G, Trinh K, Sarnyai Z and Rahimi Azghadi M (2023) Generalizable machine learning for stress monitoring from wearable devices: A systematic literature review. International Journal of Medical Informatics, 173.
Blasdell K, Morand S, Laurance S, Doggett S, Hahs A, Trinh K, Perera D and Firth C (2022) Rats and the city: Implications of urbanization on zoonotic disease risk in Southeast Asia. Proceedings of the National Academy of Sciences of the United States of America, 119 (39).
Cross J, Huo C and Trinh K (2021) Returns, volatility and the cryptocurrency bubble of 2017–18. Economic Modelling, 104.

Other research outputs

Trinh K and Cameron L (2017) Four factors driving the price Bitcoin. The Conversation,

Current Funding

Current and recent Research Funding to JCU is shown by funding source and project.

Emergency Medicine Foundation - Rural and Remote Grant

ED waiting time predictions in real-time: development of data acquisition system and performance evaluation of advanced statistical models.

Indicative Funding: $36,733 over 1 year (administered by Metro South Hospital and Health Service)
Summary: Emergency department (ED) waiting times are a significant predictor of the patient experience. This project aims to use advanced statistical models and machine-learning algorithms to capture dynamic fluctuations in waiting time, to implement and validate the prediction performance of these models. A solution that is capable of sourcing data from ED information systems and feed it into prediction models to generate waiting time forecasts would bring practical benefits for staff and patients. There is also potential to assist clinicians and nurses to estimate demand for care and calibrate workflow.
Investigators: Andrew Staib, Anton Pak and Kelly Trinh in collaboration with Rob Eley and Brenda Gannon (Metro South Hospital and Health Service, Australian Institute of Tropical Health & Medicine, College of Science & Engineering and The University of Queensland)
Keywords: Waiting time prediction; Data acquisition system; Machine learning; Emergency department

Supervision

Advisory Accreditation: I can be on your Advisory Panel as a Secondary Advisor.

These Higher Degree Research projects are either current or by students who have completed their studies within the past 5 years at JCU. Linked titles show theses available within ResearchOnline@JCU.

Current

The development of a computational model using data science approaches to predict frailty and health deficits in the elderly living in institutional care to better support the aged care system. (PhD , External Advisor)

Completed

Machine Learning for Stress Measurement using Wearable Sensor Biomarkers (2023, Masters , Secondary Advisor)

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.