mypage
Thuy T. Pham (My CV)
Email: thuy.pham at sydney.edu.au
INTERESTS:
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.
PUBLICATION:
Thuy T. Pham., Cindy Thamrin, Paul D. Robinson, Alistair McEwan, Philip H.W. Leong,"Respiratory Artefact Removal in Forced Oscillation Measurements: A Machine Learning Approach," IEEE Transactions on Biomedical Engineering 2016 (accepted). PDF Download
Thuy T. Pham, Andrew J. Fuglevand, Alistair L. McEwan, and Philip H. W. Leong, “Unsupervised discrimination of motor unit action potentials using spectrograms,” Engineering in Medicine and Biology Society (EMBC), 36th Annual International IEEE EMBS Conference, 2014. PDF Download
Thuy T. Pham and C. M. Higgins, “A visual motion detecting module for dragonfly-controlled robots,” Engineering in Medicine and Biology Society (EMBC), 36th Annual International IEEE EMBS Conference, 2014. PDF Download
Thuy T. Pham., Philip H.W. Leong, Paul D. Robinson, Cindy Thamrin, "Automated Quality Control of Forced Oscillation Measurements:Respiratory Artefact Detection with Advanced Feature Extraction," Journal of Applied Physiology (in preparation 2016).
Thuy T. Pham., Diep N. Nguyen, Eryk Dutkiewicz, Alistair L. McEwan, Cindy Thamrin, Paul D. Robinson, Philip H.W. Leong, "Feature Engineering and Supervised Learning Classifiers for Respiratory Artefact Removal in Lung Function Tests," IEEE Globecom'16 - SAC - - EH (submitted, 2016).
Thuy T. Pham., Andrew J. Fuglevand, Diep N. Nguyen, Alistair L. McEwan, Philip H.W. Leong, "Freezing of Gait Detection in Parkinson's Disease: A Subject-Independent Detector Using Anomaly Scores," IEEE Transactions on Biomedical Engineering 2016 (submitted, 2016).
THESES:
"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).
CURRENT PROJECTS:
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).
PAST PROJECTS:
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.
Source: [1]
Respiratoray artefact 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 remains 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 mannual 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.
MISC:
************** My DIY stuff **********
My home made "Lovely Vietnam": www.vnspirit.com
*************** 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