A/Prof Ting Chee Ming
School of IT
+603 5514 6079
Dr Chee-Ming Ting is an Associate Professor in the School of Information Technology, Monash University Malaysia, specializing in machine learning and data science. He was a Senior Lecturer with the School of Biomedical Engineering and Health Sciences, University Teknologi Malaysia from 2014 to 2020, and a Research Scientist with the Computer, Electrical and Mathematical Sciences & Engineering Division, King Abdullah University of Science and Technology from 2017 to 2018. Currently, he also has appointment as an Honorary Senior Research Fellow at the Division of Psychology and Language Sciences, University College London.
Dr Ting has published over 20 journal papers, 36 refereed conference papers and 6 book chapters in signal processing, medical imaging, biomedical informatics and biomedical engineering. He has served as principal investigator (PI) and co-PI for research grants from university and goverment of over RM2 millions in total. He has graduated 4 PhD and 5 Masters students, and is now supervising 4 PhD and 1 Masters students. His research interests include signal & image processing, deep neural networks, computational statistics and statistical models for networks with applications to neuroimaging and other biomedical data for automatic prediction of diseases and patient monitoring.
Dr Ting received Research Excellence Award 2019 from the IEEE Signal Processing Society Malaysia for the Best IEEE Journal Paper. He also won several national and international innovations awards. He has served as referee for over 30 journals and IEEE flagship conferences, and as member in technical and organizing committees for international conferences.
- Doctor of Philosophy (Mathematics), Universiti Teknologi Malaysia, 2012
- Master of Engineering (Electrical), Universiti Teknologi Malaysia, 2007
- Bachelor of Engineering (Hons.) (Electrical-Electronics), Universiti Teknologi Malaysia, 2005
Member of National Professional Bodies
- Board of Engineers (BEM), Malaysia, Graduate Engineer
Member of International Professional Bodies
- IEEE Signal Processing Society, Senior Member
- Biomedical signal and image analysis
- Deep learning
- Computational statistics
- Spatio-temporal modeling
- Network science
- Neuroimaging (fMRI & EEG)
- Brain connectivity analysis
- Computer-aided detection
Title: Automatic diagnosis of brain disorders using deep learning
I am working on deep neural networks to classify brain connectivity networks. Disrupted connectivity patterns are used as features to deep learning algorithms to identify neuropsychiatric diseases. With students and collaborators, we have developed a deep connectome covolutional neural network (CNN) that can identify schizophrenia from EEG connectivity with remarkable accuracy. Current research involves investigating Bayesian deep learning approach, transfer learning, autoencoders for unsupervised learning on fMRI and EEG data for detection of various brain disorders such as major depression.
Title: Dynamic brain connectivity analysis
I have been actively developing spatial-temporal models for neuroimaging data for brain connectivity analysis. We have developed Markov-switching state-space models and various extensions to examine changes in brain connectivity networks that alternate between a set of repetitive latent brain states. The method detected onset of seizure in epileptic EEGs and aberrant connectivity patterns during seizure state. Extended models also reveal dynamic brain states during resting state in large-scale fMRI data. With collaborations with psychologists, we are now developing methods to map brain dynamics from movie-watching fMRI to audio-visual stimuli to study brain response in language comprehension. The tools developed are applicable to real-time monitoring and tracking of physiological data, such as sleep and epilepsy seizure monitoring.
Title: High-dimensional statistical models for neuroimaging data
One key challenge in analyzing biomedical data is the high-dimensionality, e.g., over 100,000 voxels in a fMRI volume relative to few hundreds of scans. To overcome this, we introduced subspace vector autoregressive (VAR) models for fMRI signals which is computationally efficient to characterize massive directional dependencies in large-sized brain networks. We have also developed a multi-scale factor analysis which partitions neuroimaging data into regional clusters, and identifies low-dimensional structure in fMRI data. Currently, I am interested in low-rank and sparse modeling for neuroimaging data.
Title: Machine learning and statistical models for biological network analysis
I have been developing statistical models and machine learning tools for network analysis to study brain connectome, i.e., interactions between different brain regions as a network, which has become central to modern neuroscience in understanding human’s brain function. We have utilized graph-theoretical analysis of topological structure in brain networks to identify biomakers for neuropsychiatric disorders. We are now investigating deep learning methods to extract features from graph-structured data. We are also developing methods for community detection in brain networks in an unsupervised manner using spectral clustering. The developed tools can be broadly applicable to analyzing other real-world networks such as gene regulatory networks, social networks and etc.
- Investigating a Zero-Shot Learning Model for Improving E-Archives Architecture, Wee Mee Chin (member), 2016-2018, FRGS, Ministry of Education, RM64400
- 3D Segmentation and Visualization of Coronary Artery Using CT Image, Wee Mee Chin (member), 2013-2016, HIR, Ministry of Higher Education, RM380000
- A Novel Algorithm For Preventing Frequency of Occurrence Analysis Attack in Picture Based Password, Wee Mee Chin (member), 2012-2014, FRGS, Ministry of Education, RM64400
- A Novel Visual Representation Model of Evenness and Richness for multivariate data sets, Wee Mee Chin, 2011-2013, UMRG, University of Malaya, RM74000
- Research Excellence Award 2019 - IEEE Signal Processing Society Malaysia - IEEE Signal Processing Society Malaysia Chapter - 2019
- Silver Medal - Malaysia Technology Expo 2013 - Malaysian Association of Research Scientists - For invention/innovation of “Motor Imagery for Brain Computer Interface System”.
- Silver Medal - Malaysia Technology Expo 2013 - Malaysian Association of Research Scientists - For invention/innovation of “Smart Auditory Brainstem Response System”.
- Gold Medal - Malaysia Technology Expo 2012 - Malaysian Association of Research Scientists - For invention/innovation of “Smart ABR System”.
- Gold Medal - Malaysia Technology Expo 2012 - Malaysian Association of Research Scientists - For invention/innovation of “Designing a Multipurpose Interface use in HMI Systems Based on Facial Gesture Recognition Technology through Facial EMGs”.
- Silver Medal - International Conference and Exposition on Inventions by Institutions of Higher Learning (PECIPTA) 2013 - For invention of “Motor Imagery for Brain Computer Interface System”.
- Silver Medal- British Invention Award 2012 - British Inventions Society - For development of “Smart Auditory Brainstem Response System”.