
Fei He- PhD in Control Engineering
- Professor (Associate) at Coventry University
Fei He
- PhD in Control Engineering
- Professor (Associate) at Coventry University
SMIEEE, AE of IEEE TNSRE, co-lead of Digital Health theme.
About
86
Publications
16,480
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
923
Citations
Introduction
My research has focused on developing nonlinear systems identification, signal processing and deep learning approaches to study the complex nonlinear interactions in human brain network and diagnosis of neurological disorders (e.g. Alzheimer’s disease, epilepsy, tremor), as well as complex regulatory mechanisms in cellular (metabolic, genetic) networks. You can find the latest news of my group at https://feihelab.github.io
Current institution
Additional affiliations
Position
- Research Associate
Publications
Publications (86)
The human nervous system is one of the most complicated systems in nature. Complex nonlinear behaviours have been shown from the single neuron level to the system level. For decades, linear connectivity analysis methods, such as correlation, coherence and Granger causality, have been extensively used to assess the neural connectivities and input-ou...
Alzheimer’s disease (AD) is the leading form of dementia worldwide. AD disrupts neuronal pathways and thus is commonly viewed as a network disorder. Many studies demonstrate the power of functional connectivity (FC) graph-based biomarkers for automated diagnosis of AD using electroencephalography (EEG). However, various FC measures are commonly uti...
Alzheimer's disease (AD) is a neurodegenerative disorder known to affect functional connectivity (FC) across many brain regions. Linear FC measures have been applied to study the differences in AD by splitting neurophysiological signals, such as electroencephalography (EEG) recordings, into discrete frequency bands and analysing them in isolation f...
Graph neural network (GNN) models are increasingly being used for the classification of electroencephalography (EEG) data. However, GNN-based diagnosis of neurological disorders, such as Alzheimer’s disease (AD), remains a relatively unexplored area of research. Previous studies have relied on functional connectivity methods to infer brain graph st...
Graph neural networks (GNN) are increasingly used to classify EEG for tasks such as emotion recognition, motor imagery and neurological diseases and disorders. A wide range of methods have been proposed to design GNN-based classifiers. Therefore, there is a need for a systematic review and categorisation of these approaches. We exhaustively search...
Despite significant advances in deep learning-based sleep stage classification, the clinical adoption of automatic classification models remains slow. One key challenge is the lack of explainability, as many models function as black boxes with millions of parameters. In response, recent work has increasingly focussed on enhancing model explainabili...
Electroencephalography (EEG), as a well-established, non-invasive tool, has been successfully applied to a wide range of conditions due to its many evident advantages, such as economy, portability, easy operation, easy accessibility, and widespread availability in hospitals [...]
Recent advancements in machine learning-based signal analysis, coupled with open data initiatives, have fuelled efforts in automatic sleep stage classification. Despite the proliferation of classification models, few have prioritised reducing model complexity, which is a crucial factor for practical applications. In this work, we introduce Multi-Sc...
Electroencephalogram (EEG) is a valuable technique to record brain electrical activity through electrodes placed on the scalp. Analyzing EEG signals contributes to the understanding of neurological conditions and developing brain-computer interface. Graph Signal Processing (GSP) has emerged as a promising method for EEG spatial-temporal analysis, b...
System identification involves constructing mathematical models of dynamic systems using input-output data, enabling analysis and prediction of system behaviour in both time and frequency domains. This approach can model the entire system or capture specific dynamics within it. For meaningful analysis, it is essential for the model to accurately re...
In smart greenhouse farming, the impact of light qualities on plant growth and development is crucial but lacks systematic identification of optimal combinations. This study addresses this gap by analysing various light properties’ effects (photoperiod, intensity, ratio, light–dark order) on Arabidopsis thaliana growth using days-to-flower (DTF) an...
In order to feed the ever-increasing global population, current food production must increase significantly in the near future. Increasing food production by expanding farmland or by farming intensification would lead to increasing land-use demand, which comes at the cost of biodiversity, increasing pressure on vulnerable ecosystems, and requiring...
In this work, we explore information geometry theoretic measures for characterizing neural information processing from EEG signals simulated by stochastic nonlinear coupled oscillator models for both healthy subjects and Alzheimer’s disease (AD) patients with both eyes-closed and eyes-open conditions. In particular, we employ information rates to q...
Multivariate signals measured simultaneously over time by sensor networks are becoming increasingly common. The emerging field of graph signal processing (GSP) promises to analyse spectral characteristics of these multivariate signals, while also taking the spatial structure between the time signals into account. A core idea in GSP is the graph Fou...
Multivariate signals, which are measured simultaneously over time and acquired by sensor networks, are becoming increasingly common. The emerging field of graph signal processing (GSP) promises to analyse spectral characteristics of these multivariate signals, while at the same time taking the spatial structure between the time signals into account...
In this work, we explore information geometry theoretic approach to analyzing EEG signals simulated by stochastic nonlinear coupled oscillator models for both healthy subjects and Alzheimer’s Disease (AD) patients with both eyes-closed and eyes-open conditions. In particular, we employ information rates to quantify the time evolution of probability...
Signals measured with multiple sensors simultaneously in time form multivariate signals and are commonly acquired in biomedical imaging. These temporal signals are generally not independent of each other, but exhibit a rich spatial structure. Graph filtering, either spatial or spectral, is a method that can leverage this spatial structure for vario...
1. Background Electroencephalography (EEG) is a widely recognised non-invasive method for capturing brain electrophysiological activity. It stands out for its cost-effectiveness, portability, ease of administration, and widespread availability in most hospital settings. Unlike other neuroimaging modalities focused on anatomical structure, such as M...
In smart greenhouse farming, artificially adjustable light qualities (colours) play an important role to promote plant growth. While it is known that these light qualities have significant impacts on plant development, the suitable combinations enabling the plant to grow at its best are yet to be systematically identified. This study fills this gap...
Dynamical, causal, and cross-frequency coupling analysis using the electroencephalogram (EEG) has gained significant attention for diagnosing and characterizing neurological disorders. Selecting important EEG channels is crucial for reducing computational complexity in implementing these methods and improving classification accuracy. In neuroscienc...
The quantification of causality is vital for understanding various important phenomena in nature and laboratories, such as brain networks, environmental dynamics, and pathologies. The two most widely used methods for measuring causality are Granger Causality (GC) and Transfer Entropy (TE), which rely on measuring the improvement in the prediction o...
Graph neural network (GNN) models are increasingly being used for the classification of electroencephalography (EEG) data. However, GNN-based diagnosis of neurological disorders, such as Alzheimer's disease (AD), remains a relatively unexplored area of research. Previous studies have relied on functional connectivity methods to infer brain graph st...
Parkinson’s disease (PD) is a neurodegenerative disorder that affects millions of people worldwide. Its slow and heterogeneous progression over time makes timely diagnosis challenging. Wrist-worn digital devices, particularly smartwatches, are currently the most popular tools in the PD research field due to their convenience for long-term daily lif...
For the characterisation and diagnosis of neurological disorders, dynamical, causal and cross-frequency coupling analysis using the EEG has gained considerable attention. Due to high computational costs in implementing some of these methods, the selection of important EEG channels is crucial. The channel selection method should be able to accommoda...
Alzheimer's disease (AD) is a neurodegenerative disease known to affect brain functional connectivity (FC). Linear FC measures have been applied to study the differences in AD by splitting neurophysiological signals such as electroencephalography (EEG) recordings into discrete frequency bands and analysing them in isolation. We address this limitat...
Recent advances in synthetic biology have enabled the design of genetic feedback control circuits that could be implemented to build resilient plants against pathogen attacks. To facilitate the proper design of these genetic feedback control circuits, an accurate model that is able to capture the vital dynamical behaviour of the pathogen-infected p...
Alzheimer's disease (AD) is the leading form of dementia in the world. AD disrupts neuronal pathways and thus is commonly viewed as a network disorder. Many studies demonstrate the power of functional connectivity (FC) graph-based biomarkers for automated diagnosis of AD using electroencephalography (EEG). However, various FC measures are commonly...
Alzheimer's disease (AD) is a neurodegenerative disease known to affect brain functional connectivity (FC). Linear FC measures have been applied to study the differences in AD by splitting neurophysiological signals such as electroencephalography (EEG) recordings into discrete frequency bands and analysing them in isolation. We address this limitat...
Background
Many physical, biological and neural systems behave as coupled oscillators, with characteristic phase coupling across different frequencies. Methods such as n:m phase locking value (where two coupling frequencies are linked as: mf1=nf2) and bi-phase locking value have previously been proposed to quantify phase coupling between two resona...
Recent advances in synthetic biology have enabled the design of genetic feedback control circuits that could be implemented to build resilient plants against pathogen attacks. To facilitate the proper design of these genetic feedback control circuits, an accurate model that is able to capture the vital dynamical behaviour of the pathogen-infected p...
Alzheimer's disease (AD) is one of the most common neurodegenerative diseases, with around 50 million patients worldwide. Accessible and non-invasive methods of diagnosing and characterising AD are therefore urgently required. Electroencephalography (EEG) fulfils these criteria and is often used when studying AD. Several features derived from EEG w...
Alzheimer's disease (AD) is a neurodegenerative disorder known to affect functional connectivity (FC) across many brain regions. Linear FC measures have been applied to study the differences in AD by splitting neurophysiological signals such as electroencephalography (EEG) recordings into discrete frequency bands and analysing them in isolation fro...
The importance of an optimal solution for disaster evacuation has recently raised attention from researchers across multiple disciplines. This is not only a serious, but also a challenging task due to the complexities of the evacuees’ behaviors, route planning, and demanding coordination services. Although existing studies have addressed these chal...
Many physical, biological and neural systems behave as coupled oscillators, with characteristic phase coupling across different frequencies. Methods such as $n:m$ phase locking value and bi-phase locking value have previously been proposed to quantify phase coupling between two resonant frequencies (e.g. f, 2f/3) and across three frequencies (e.g....
Alzheimer's disease (AD) is one of the most common neurodegenerative diseases, with around 50 million patients worldwide. Accessible and non-invasive methods of diagnosing and characterising AD are therefore urgently required. Electroencephalography (EEG) fulfils these criteria and is often used when studying AD. Several features derived from EEG w...
The human nervous system is one of the most complicated systems in nature. The complex nonlinear behaviours have been shown from the single neuron level to the system level. For decades, linear connectivity analysis methods, such as correlation, coherence and Granger causality, have been extensively used to assess the neural connectivities and inpu...
In this work, nonlinear temporal features from multi-channel EEGs are used for the classification of Alzheimer's disease patients from healthy individuals. This was achieved by temporal manifold learning using Gaussian Process Latent Variable Models (GPLVM) as a nonlinear dimensionality reduction technique. Classification of the extracted features...
Motivation:
Approximate Bayesian computation (ABC) is an important framework within which to infer the structure and parameters of a systems biology model. It is especially suitable for biological systems with stochastic and nonlinear dynamics, for which the likelihood functions are intractable. However, the associated computational cost often lim...
One of the central tasks in systems biology is to understand how cells regulate their metabolism. Hierarchical regulation analysis (HRA) is a powerful tool to study this regulation at the metabolic, gene-expression and signaling levels. It has been widely applied to study the steady-state regulation; but analysis of the metabolic dynamics remains c...
Background
Reverse engineering of gene regulatory networks from time series gene-expression data is a challenging problem, not only because of the vast sets of candidate interactions but also due to the stochastic nature of gene expression. We limit our analysis to nonlinear differential equation based inference methods. In order to avoid the compu...
Background: The incidence of Alzheimer disease (AD) is increasing with the ageing population. The development of low cost non-invasive diagnostic aids for AD is a research priority. This pilot study investigated whether an approach based on a novel dynamic quantitative parametric EEG method could detect abnormalities in people with AD. Methods: 20...
Reverse engineering of gene regulatory networks from time series gene-expression data is a challenging problem, not only because of the vast sets of candidate interactions but also due to the stochastic nature of gene expression. To avoid the computational cost of large-scale simulations, a two-step Gaussian process interpolation based gradient mat...
Objective
To determine the origin and dynamic characteristics of the generalised hyper-synchronous spike and wave (SW) discharges in childhood absence epilepsy (CAE).
Methods
We applied nonlinear methods, the error reduction ratio (ERR) causality test and cross-frequency analysis, with a nonlinear autoregressive exogenous (NARX) model, to electroe...
Introduction
Quantitative Electroencephalography (qEEG) has been shown to distinguish AD patients from healthy controls (HC) at a group but not at an individual level. A novel qEEG data analysis method created at the University of Sheffield can measure linear and non-linear levels of brain synchronisation in the time domain.
Methods
Patients with...
Metabolic pathways can be engineered to maximize the synthesis of various products of interest. With the advent of computational systems biology, this endeavour is usually carried out through in silico theoretical studies with the aim to guide and complement further in vitro and in vivo experimental efforts. Clearly, what counts is the result in vi...
There is increasing evidence to suggest that essential tremor has a central origin. Different structures appear to be part of the central tremorogenic network, including the motor cortex, the thalamus and the cerebellum. Some studies using EEG and MEG show linear association in the tremor frequency between the motor cortex and the contralateral tre...
Living organisms persist by virtue of complex interactions among many components organized into dynamic, environment-responsive networks that span multiple scales and dimensions. Biological networks constitute a type of Information and Communication Technology (ICT): they receive information from the outside and inside of cells, integrate and inter...
Selective catalytic reduction (SCR) system is a complex chemical process which is used to treat exhaust gas in many applications, e.g. diesel engines in automobiles. An SCR model was constructed by General Motors (GM) and the problem considered was to estimate the unknown kinetic parameters on-line taking into account aging effects. There are a num...
Background: Frequency domain Granger causality measures have been proposed and widely applied in
analyzing rhythmic neurophysiological and biomedical signals. Almost all these measures are based on
linear time domain regression models, and therefore can only detect linear causal effects in the frequency
domain.
New method: A frequency domain causal...
Systems Biology brings the potential to discover fundamental principles of Life that cannot be discovered by considering individual molecules. This chapter discusses a number of early, more recent and upcoming discoveries of such network principles. These range from the balancing of fluxes through metabolic networks, the potential of those networks...
Spectral measures of linear Granger causality have been widely applied to study the causal connectivity between time series data in neuroscience, biology, and economics. Traditional Granger causality measures are based on linear autoregressive with exogenous (ARX) inputs models of time series data, which cannot truly reveal nonlinear effects in the...
Metabolic control analysis (MCA) and supply--demand theory have led to appreciable understanding of the systems properties of metabolic networks that are subject exclusively to metabolic regulation. Supply--demand theory has not yet considered gene-expression regulation explicitly whilst a variant of MCA, i.e. Hierarchical Control Analysis (HCA), h...
This paper introduces a new approach for nonlinear and non-stationary (time-varying) system identification based on time-varying nonlinear autoregressive moving average with exogenous variable (TV-NARMAX) models. The challenging model structure selection and parameter tracking problems are solved by combining a multiwavelet basis function expansion...
A new frequency domain analysis framework for nonlinear time-varying systems is introduced based on parametric time-varying NARX models. It is shown how the time-varying effects can be mapped to the generalized frequency response functions to track nonlinear features in frequency, such as inter-modulation and energy transfer effects. A new mapping...
A new NARX-based Granger linear and nonlinear casual influence detection method is presented in this paper to address the potential for linear and nonlinear models in data with applications to human EEG data analysis. Considering two signals initially, the paper introduces four indexes to measure the linearity and nonlinearity of a single signal, a...
The purpose of model-based experimental design is to maximise the information gathered for quantitative model identification. Instead of the commonly used optimal experimental design, robust experimental design aims to address parametric uncertainties in the design process. In this paper, the Bayesian robust experimental design is investigated, whe...
The purpose of model-based experimental design is to maximise the information gathered for
quantitative model identification. Instead of the commonly used optimal experimental design, robust
experimental design aims to address parametric uncertainties in the design process. In this paper, the
Bayesian robust experimental design is investigated, whe...
Experimental design is important in system identification, especially when the models are complex and the measurement data are sparse and noisy, as often occurs in modelling of biochemical regulatory networks. The quality of conventional optimal experimental design largely depends on the accuracy of model parameter estimation, which is often either...
An important aspect of systems biology research is the so-called "reverse engineering" of cellular metabolic dynamics from measured input-output data. This allows researchers to estimate and validate both the pathway's structure as well as the kinetic constants. In this paper, the recently published 'Proximate Parameter Tuning' (PPT) method for the...
Experimental design for cellular networks based on sensitivity analysis is studied in this work. Both optimal and robust experimental design strategies are developed for the IkappaB-NF-kappaB signal transduction model. Based on local sensitivity analysis, the initial IKK intensity is calculated using an optimal experimental design process, and seve...
An important aspect of systems biology research is the so-called ldquoreverse engineeringrdquo of cellular metabolic dynamics from measured input-output data. This allows researchers to estimate and validate both the pathwaypsilas structure as well as the kinetic constants. In this paper, a regularization based method which performs model structure...
Due to the general lack of experimental data for biochemical pathway model identification, cell-level time series experimental design is particularly important in current systems biology research. This paper investigates the problem of experimental design for signal transduction pathway modeling, and in particular, focuses on methods for parametric...
Based on much experimentation, traditional biochemists and molecular biologists have developed many qualitative models and
hypotheses for biochemical pathway study [7, 26, 28]. However, in order to evaluate the completeness and usefulness of a hypothesis,
produce predictions for further testing, and better understand the interaction and dynamic of...
As a general lack of quantitative measurement data for pathway modelling and parameter identification process, time-series experimental design is particularly important in current systems biology research. This paper mainly investigates state measurement/observer selection problem when parametric uncertainties are considered. Based on the extension...
Parameter estimation of non-linear differential equations has long been an active and challenge research area. Conventionally methods are computationally intensive and often poorly conditioned. In the context of biochemical pathway modeling, a new method focused on this paper is the so-called "collocation" method, which is a nonparametric data smoo...
This paper presents the importance of formulating general discrete-time model representations for current pathway deterministic modeling study. Discrete-time models can be considered as a link between continuous-time kinetic reactions and discrete-time experimentation as well as computer based simulation and analysis. In the paper, different discre...
This paper presents the importance of formulating general discrete-time model representations for current pathway modeling study. Discrete-time models can be considered as a link between continuous-time kinetic reactions and discrete-time experimentation as well as computer based simulation and analysis. In the paper, different discretization techn...