Thuy T. Pham 

Postdoctoral Research Associate at FEIT Faculty, UTS.

Email: thuy.pham at or at

Ph.D. at The University of Sydney/ EIE 




Biomedical wearable devices for in-lab or out-of-lab deployment with solutions in

•Hardware platform

•Applied machine learning

•Fashion: Big data, Internet of things, or data science.




Journal articles

Pham, T.T., Leong, P.H.W., Robinson, P.D. & Thamrin, C. 2017, 'Automated Quality Control of Forced Oscillation Measurements: Respiratory Artefact Detection with Advanced Feature Extraction', Journal of Applied Physiology. Accepted 2017.

Pham, T.T., Moore, S.T., Lewis, S.J.G., Nguyen, D.N., Dutkiewicz, E., Fuglevand, A.J., McEwan, A.L. & Leong, P.H.W. 2017, 'Freezing of Gait Detection in Parkinson's Disease: A Subject-Independent Detector Using Anomaly Scores', IEEE Transactions on Biomedical Engineering.
View/Download from: 
Publisher's site

Pham, T.T., Thamrin, C., Robinson, P.D., McEwan, A. & Leong, P.H.W. 2016, 'Respiratory Artefact Removal in Forced Oscillation Measurements: A Machine Learning Approach', IEEE Transactions on Biomedical Engineering, pp. 1-1.

View/Download from: Publisher's site




Pham, T.T.Nguyen, D.N., Dutkiewicz, E., McEwan, A.L. & Leong, P.H.W. 2017, 'Wearable Healthcare Systems: A Single Channel Accelerometer Based Anomaly Detector for Studies of Gait Freezing in Parkinson's Disease', Proceedings of the IEEE, IEEE conference ICC'17 SAC-6 EH, Institute of Electrical and Electronics Engineers. May 2017, Paris, France.


Pham, T.T.Nguyen, D.N.Dutkiewicz, E., McEwan, A.L., Thamrin, C., Robinson, P.D. & Leong, P.H.W. 2017, 'Feature engineering and supervised learning classifiers for respiratory artefact removal in lung function tests', 2016 IEEE Global Communications Conference, GLOBECOM 2016 - ProceedingsDec 2016, Washington DC, USA.

View/Download from: UTS OPUS or Publisher's site

View description >


Pham, T.Nguyen, D., Dutkiewicz, E., McEwan, A. & Leong, P. 2017, 'An Anomaly Detection Technique in Wearable Wireless Monitoring Systems for Studies of Gait', 31st International Conference on Information Networking (ICOIN). Jan 2017, Danang, Vietnam.

Pham, T.T., Fuglevand, A.J., McEwan, A.L. & Leong, P.H.W. 2014, 'Unsupervised discrimination of motor unit action potentials using spectrograms', Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE, IEEE, pp. 1-4. Aug 2014, Chicago, IL USA.

Pham, T.T. & Higgins, C.M. 2014, 'A visual motion detecting module for dragonfly-controlled robots', Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE, IEEE, pp. 1666-1669. Chicago, IL USA.





•"Automated Classification for Biomedical Data: Machine Learning Approaches for Subject-Independent Settings," at The Computer Engineering Lab, The University of Sydney, NSW, Australia (2016).

•"A real-time neural signal processing system for dragonflies," at The Higgins Laboratory, Neuromorphic Vision and Robotic Systems, The University of Arizona, Arizona USA (12/2011 Class of 2012).



Automated Classification for Biomedical Data: Machine Learning Approaches for Subject-Independent Settings

•Freezing of gait detection for Parkinson's disease.

•Data analysis with NICU Department, Westmead hospital, Sydney NSW AUS.

•Respiratoray artefact removal in FOT lung function test data (with Woolcock).

Source: [1]

Freezing of gait detection in Parkinson's disease with acceleration data:

Studies in freezing of gait (FoG) can help prevent falls and understand the causality. Our feature engineering helps finding novel features that are more relevant and discriminative. Our FoG detectors which, to the best of our knowledge, achieve the best reported performance for unsupervised subject-independent settings for FoG data. Future work may lead to a device which provides cues for patients with Parkinson's disease.

Respiratory artifact removal in FOT lung function test:

Forced oscillation technique (FOT) is non-invasive, non-effort dependent, thus is for patients too young or unable to perform other pulmonary testing. However currently it has low repeatability due to remain respiratory artifacts. We used feature engineering and anomaly detection techniques to offer better objective quality control.

Source: [2]


Automatic spike sorting for electrophysiological recordings:

Needle EMG analysis can provide information about active motor units in neurological experiments. Current manual sorting of motor units can cost hours of neurologists. We offer a simple automated method using correlation based unsupervised spike sorting technique.

Source: [3][4]


Building hybrid bio-robot systems with both artificial components and real biological components:

Online hardware-based electrophysiological signal processing is desirable for brain machine interface applications with neural recordings. One example of this research topic is the interface between insect's brain and a hardware platform. Visual receptive field of insect’s eyes can be used to guide a robot platform in hybrid bio-robots or close-loop control experiments in neuroscience. We offer an online action potential discrimination algorithm for the interface module. 8 target selective descending neuron (TSDN) templates have been built for a direction signal detection.

•Spike sorting visual response signals in real-time for a dragonfly bio-robot, Spring 2011.

•Fabricating signal processing PCBs for extracellular signal recordings, Fall 2010.

•Designing a digital signal processing PCB with a FPGA-based microprocessor, Summer 2010.

The Higgins Laboratory, Neuromorphic Vision and Robotic Systems

Professor Charles Higgins, University of Arizona




Thuy Pham is currently a Ph.D candidate in electrical and information engineering at The University of Sydney, NSW, Australia. Thuy's passion for signal processing started at The University of Arizona, USA in a Electrical and Computer Engineering MSc program in 2010, where she built her background on Neuroscience, Robotics, Digital Signal and Image Processing. She was awarded the UA Meritorious Awards (2010-2012) and the Progressing Research Grant, Neuroscience Dept., for her thesis on a real-time neural signal processing system for dragonflies towards hybrid bio-robots, at The Higgins Laboratory, Neuromorphic Vision and Robotic Systems, The University of Arizona.  

Upon receiving the Australian Prime Minister Award (Endeavour, 2013-2017) and Norman I. Price Scholarship for her PhD study, Thuy picked up interests in machine learning. Her PhD thesis, titled "Automated Classification for Biomedical Data: Machine Learning Approaches for Subject-Independent Settings”. She has been held visiting scholar appointments and collaborated with world-leading medical and physiology groups. At the Fuglevand Laboratory on Motor Control Neurophysiology, USA, she explored unsupervised spike sorting methods using machine-learning techniques to automate action potential discrimination. At Brain & Mind Research Institute, Sydney Medical School, she developed algorithms towards medical wearable devices, e.g., a real-time monitor for freezing of gait events in patients with advanced Parkinson’s disease. At Woolcock Institute of Medical Research, NSW, Thuy enjoys the dual challenge of applying advanced machine learning and statistics to improve quality control of lung function tests, and embedding a data-first culture. Part of her work on feature engineering and classification has been published on several IEEE Transactions on Biomedical Engineering and conferences.




************** My DIY stuff *******************************

"Lovely Vietnam":


*************** Recommend to you **************************

Worlds Largest Cave Discovered In Vietnam!

OFFICIAL New 7 Wonders of the World

Welcome to Halong Bay, Vietnam



Source Photos: [1] Snijders et al. N Engl J Med 2010 [2] MasterScreen™ [3] “Principles of Neural Science” 4th_Edition, 2000 by Kandel et al. [4] Photo: Fuglevand lab