My current research interests lie at the interface of control systems engineering, signal processing and neuroscience/biology. Over the years, I have been developing nonlinear system identification and frequency-domain techniques to study complex nonlinear interactions in human brain network, and use such nonlinear features to improve the diagnosis of neurological disorders, such as Alzheimer’s disease and seizures, from neurophysiological signals like electroencephalogram (EEG). I am also interested in statistical machine learnig, network inference and their applications in neuroscience and systems biology, such as identifying complex regulatory mechanisms in cellular (metabolic, genetic) networks.

Currently, I co-lead the 'Digital Health' Cross Cutting Theme at Coventry University. I am a member of the UKRI Future Leaders Fellowships (FLF) peer review college, a Senior Member of IEEE. I am the Associate Editor of IET Healthcare Technology Letters, editorial board member of Frontiers in Computational Neuroscience/Neuroinformatics, and a reviewer for international funding bodies, including EPSRC and Royal Society. I previously held research positions at Imperial College London (Theoretical Systems Biology group), University of Sheffield, and University of Manchester (Manchester Centre for Integrative Systems Biology). I received a PhD and an MSc (distinction) in control engineering from University of Manchester.

For more details about my group's research, please visit my personal webpage at: feihelab.github.io

Teaching:

• Module leader - 7089CEM, Introduction to Statistical Methods for Data Science
• Module leader - 7037CEM, Machine Learning
• Lecturer - 230MP Advanced Matlab: Data Science and ML
• Supervisor - 300COM Final year project, M08CDE MSc project
• Module leader - CPE6005/CPE422 Bio-systems Engineering and Computational Biology, 2015 - 2017, University of Sheffield.

Computational Neuroscience - Nonlinear systems identification, Signal processing and Causality analysis

• NARMAX model-based nonlinear frequency analysis & causality analysis
• Nonlinear time-frequency modelling and diagnosis of neurological disorders (e.g. seizures, Alzheimer’s disease) based on neurophysiological recordings: EEG, EMG, fMRI

Computational Systems Biology

• Bayesian inference for parameter estimation and model selection
• Optimal and Bayesian model-based experimental design
• Network inference for complex biochemical regulatory pathways

Projects & Grants:

• PI, EPSRC (EP/X020193/1), Characterising Neurological Disorders with Nonlinear System Identification and Network Analysis, Dec 2023 - May 2026.
• Co-I, EPSRC (EP/W036770/1), Information geometric theory of neural information processing and disorder, Feb 2023 – Feb 2024.
• Co-I, EPSRC N-code (EP/W035030/1) seed project, Non-invasive Brain-computer-interfaces for Remote Rehab and Training of Motor Skills, Dec 2023 - Dec 2024.

If you are interested to do a PhD in statistical machine learning, nonlinear signal processing/system identification, network science with possible applications in neuroscience or systems biology, or apply for a postdoc Fellowship or a visiting position, please get in touch with me. Currently, I have the following position open (please email me your CV first):

• A fully-funded PhD studentship for Jan 2024 start, on the topic of dynamical system, deep learning, and brain network (see link for details).
• A fully-funded joint PhD studentship (with A*STAR) for Jan 2024 start, on 'Deep Learning on Neurophysiological Signals for Characterising Neurodegenerative Diseases'.