Publications
2021
Jin, Jing; Sun, Hao; Daly, Ian; Li, Shurui; Liu, Chang; Wang, Xingyu; Cichocki, Andrzej
A Novel Classification Framework Using the Graph Representations of Electroencephalogram for Motor Imagery based Brain-Computer Interface Journal Article
In: IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021.
Abstract | Links | BibTeX | Tags: BCI, Classification, EEG, ERD, Functional connectivity, Motor imagery
@article{Jin2021Graph,
title = {A Novel Classification Framework Using the Graph Representations of Electroencephalogram for Motor Imagery based Brain-Computer Interface},
author = {Jing Jin and Hao Sun and Ian Daly and Shurui Li and Chang Liu and Xingyu Wang and Andrzej Cichocki},
doi = {10.1109/TNSRE.2021.3139095},
year = {2021},
date = {2021-12-28},
journal = {IEEE Transactions on Neural Systems and Rehabilitation Engineering},
abstract = {The motor imagery (MI) based brain-computer interfaces (BCIs) have been proposed as a potential physical rehabilitation technology. However, the low classification accuracy achievable with MI tasks is still a challenge when building effective BCI systems. We propose a novel MI classification model based on measurement of functional connectivity between brain regions and graph theory. Specifically, motifs describing local network structures in the brain are extracted from functional connectivity graphs. A graph embedding model called Ego-CNNs is then used to build a classifier, which can convert the graph from a structural representation to a fixed-dimensional vector for detecting critical structure in the graph. We validate our proposed method on four datasets, and the results show that our proposed method produces high classification accuracies in two-class classification tasks (92.8% for dataset 1, 93.4% for dataset 2, 96.5% for dataset 3, and 80.2% for dataset 4) and multiclass classification tasks (90.33% for dataset 1). Our proposed method achieves a mean Kappa value of 0.88 across nine participants, which is superior to other methods we compared it to. These results indicate that there is a local structural difference in functional connectivity graphs extracted under different motor imagery tasks. Our proposed method has great potential for motor imagery classification in future studies.},
keywords = {BCI, Classification, EEG, ERD, Functional connectivity, Motor imagery},
pubstate = {published},
tppubtype = {article}
}
The motor imagery (MI) based brain-computer interfaces (BCIs) have been proposed as a potential physical rehabilitation technology. However, the low classification accuracy achievable with MI tasks is still a challenge when building effective BCI systems. We propose a novel MI classification model based on measurement of functional connectivity between brain regions and graph theory. Specifically, motifs describing local network structures in the brain are extracted from functional connectivity graphs. A graph embedding model called Ego-CNNs is then used to build a classifier, which can convert the graph from a structural representation to a fixed-dimensional vector for detecting critical structure in the graph. We validate our proposed method on four datasets, and the results show that our proposed method produces high classification accuracies in two-class classification tasks (92.8% for dataset 1, 93.4% for dataset 2, 96.5% for dataset 3, and 80.2% for dataset 4) and multiclass classification tasks (90.33% for dataset 1). Our proposed method achieves a mean Kappa value of 0.88 across nine participants, which is superior to other methods we compared it to. These results indicate that there is a local structural difference in functional connectivity graphs extracted under different motor imagery tasks. Our proposed method has great potential for motor imagery classification in future studies.
2018
Williams, Nitin Jonathan; Daly, Ian; Nasuto, Slawomir
Markov Model-based method to analyse time-varying networks in EEG task-related data Journal Article
In: Frontiers in Computational Neuroscience, 2018.
BibTeX | Tags: EEG, Functional connectivity
@article{WilliamsN2018,
title = {Markov Model-based method to analyse time-varying networks in EEG task-related data},
author = {Nitin Jonathan Williams and Ian Daly and Slawomir Nasuto},
year = {2018},
date = {2018-08-20},
journal = {Frontiers in Computational Neuroscience},
keywords = {EEG, Functional connectivity},
pubstate = {published},
tppubtype = {article}
}
2014
Daly, Ian; Malik, Asad; Hwang, Faustina; Roesch, Etienne; Weaver, James; Kirke, Alexis; Williams, Duncan; Miranda, Eduardo; Nasuto, Slawomir J.
Neural correlates of emotional responses to music: an EEG study Journal Article
In: Neuroscience letters, vol. 573, pp. 52–57, 2014.
Abstract | Links | BibTeX | Tags: Asymmetry, EEG, Emotion, Functional connectivity, Music
@article{Daly2014NC,
title = {Neural correlates of emotional responses to music: an EEG study},
author = {Ian Daly and Asad Malik and Faustina Hwang and Etienne Roesch and James Weaver and Alexis Kirke and Duncan Williams and Eduardo Miranda and Slawomir J. Nasuto},
url = {http://www.iandaly.co.uk/wp-content/uploads/2016/01/Neural-correlates-of-emotional-responses-to-music-an-EEG-study-pub.pdf},
doi = {10.1016/j.neulet.2014.05.003},
year = {2014},
date = {2014-06-24},
journal = {Neuroscience letters},
volume = {573},
pages = {52–57},
abstract = {This paper presents an EEG study into the neural correlates of music-induced emotions. We presented participants with a large dataset containing musical pieces in different styles, and asked them to report on their induced emotional responses.
We found neural correlates of music-induced emotion in a number of frequencies over the pre-frontal cortex. Additionally, we found a set of patterns of functional connectivity, defined by inter-channel coherence measures, to be significantly different between groups of music-induced emotional responses.},
keywords = {Asymmetry, EEG, Emotion, Functional connectivity, Music},
pubstate = {published},
tppubtype = {article}
}
This paper presents an EEG study into the neural correlates of music-induced emotions. We presented participants with a large dataset containing musical pieces in different styles, and asked them to report on their induced emotional responses.
We found neural correlates of music-induced emotion in a number of frequencies over the pre-frontal cortex. Additionally, we found a set of patterns of functional connectivity, defined by inter-channel coherence measures, to be significantly different between groups of music-induced emotional responses.
We found neural correlates of music-induced emotion in a number of frequencies over the pre-frontal cortex. Additionally, we found a set of patterns of functional connectivity, defined by inter-channel coherence measures, to be significantly different between groups of music-induced emotional responses.
Müller-Putz, Gernot; Daly, Ian; Kaiser, Vera
Motor imagery induced EEG patterns in spinal cord injury patients and their impact on Brain-Computer Interface accuracy Journal Article
In: Journal of Neural Engineering, vol. 11, no. 3, pp. 1-9, 2014.
Abstract | Links | BibTeX | Tags: BCI, ERD, Functional connectivity, Motor imagery, SCI
@article{Muller-Putz2014,
title = {Motor imagery induced EEG patterns in spinal cord injury patients and their impact on Brain-Computer Interface accuracy},
author = {Gernot Müller-Putz and Ian Daly and Vera Kaiser},
url = {http://www.ncbi.nlm.nih.gov/pubmed/24835837},
doi = {10.1088/1741-2560/11/3/035011},
year = {2014},
date = {2014-06-01},
journal = {Journal of Neural Engineering},
volume = {11},
number = {3},
pages = {1-9},
abstract = {OBJECTIVE:
Assimilating the diagnosis complete spinal cord injury (SCI) takes time and is not easy, as patients know that there is no 'cure' at the present time. Brain-computer interfaces (BCIs) can facilitate daily living. However, inter-subject variability demands measurements with potential user groups and an understanding of how they differ to healthy users BCIs are more commonly tested with. Thus, a three-class motor imagery (MI) screening (left hand, right hand, feet) was performed with a group of 10 able-bodied and 16 complete spinal-cord-injured people (paraplegics, tetraplegics) with the objective of determining what differences were present between the user groups and how they would impact upon the ability of these user groups to interact with a BCI.
APPROACH:
Electrophysiological differences between patient groups and healthy users are measured in terms of sensorimotor rhythm deflections from baseline during MI, electroencephalogram microstate scalp maps and strengths of inter-channel phase synchronization. Additionally, using a common spatial pattern algorithm and a linear discriminant analysis classifier, the classification accuracy was calculated and compared between groups.
MAIN RESULTS:
It is seen that both patient groups (tetraplegic and paraplegic) have some significant differences in event-related desynchronization strengths, exhibit significant increases in synchronization and reach significantly lower accuracies (mean (M) = 66.1%) than the group of healthy subjects (M = 85.1%).
SIGNIFICANCE:
The results demonstrate significant differences in electrophysiological correlates of motor control between healthy individuals and those individuals who stand to benefit most from BCI technology (individuals with SCI). They highlight the difficulty in directly translating results from healthy subjects to participants with SCI and the challenges that, therefore, arise in providing BCIs to such individuals.},
keywords = {BCI, ERD, Functional connectivity, Motor imagery, SCI},
pubstate = {published},
tppubtype = {article}
}
OBJECTIVE:
Assimilating the diagnosis complete spinal cord injury (SCI) takes time and is not easy, as patients know that there is no 'cure' at the present time. Brain-computer interfaces (BCIs) can facilitate daily living. However, inter-subject variability demands measurements with potential user groups and an understanding of how they differ to healthy users BCIs are more commonly tested with. Thus, a three-class motor imagery (MI) screening (left hand, right hand, feet) was performed with a group of 10 able-bodied and 16 complete spinal-cord-injured people (paraplegics, tetraplegics) with the objective of determining what differences were present between the user groups and how they would impact upon the ability of these user groups to interact with a BCI.
APPROACH:
Electrophysiological differences between patient groups and healthy users are measured in terms of sensorimotor rhythm deflections from baseline during MI, electroencephalogram microstate scalp maps and strengths of inter-channel phase synchronization. Additionally, using a common spatial pattern algorithm and a linear discriminant analysis classifier, the classification accuracy was calculated and compared between groups.
MAIN RESULTS:
It is seen that both patient groups (tetraplegic and paraplegic) have some significant differences in event-related desynchronization strengths, exhibit significant increases in synchronization and reach significantly lower accuracies (mean (M) = 66.1%) than the group of healthy subjects (M = 85.1%).
SIGNIFICANCE:
The results demonstrate significant differences in electrophysiological correlates of motor control between healthy individuals and those individuals who stand to benefit most from BCI technology (individuals with SCI). They highlight the difficulty in directly translating results from healthy subjects to participants with SCI and the challenges that, therefore, arise in providing BCIs to such individuals.
Assimilating the diagnosis complete spinal cord injury (SCI) takes time and is not easy, as patients know that there is no 'cure' at the present time. Brain-computer interfaces (BCIs) can facilitate daily living. However, inter-subject variability demands measurements with potential user groups and an understanding of how they differ to healthy users BCIs are more commonly tested with. Thus, a three-class motor imagery (MI) screening (left hand, right hand, feet) was performed with a group of 10 able-bodied and 16 complete spinal-cord-injured people (paraplegics, tetraplegics) with the objective of determining what differences were present between the user groups and how they would impact upon the ability of these user groups to interact with a BCI.
APPROACH:
Electrophysiological differences between patient groups and healthy users are measured in terms of sensorimotor rhythm deflections from baseline during MI, electroencephalogram microstate scalp maps and strengths of inter-channel phase synchronization. Additionally, using a common spatial pattern algorithm and a linear discriminant analysis classifier, the classification accuracy was calculated and compared between groups.
MAIN RESULTS:
It is seen that both patient groups (tetraplegic and paraplegic) have some significant differences in event-related desynchronization strengths, exhibit significant increases in synchronization and reach significantly lower accuracies (mean (M) = 66.1%) than the group of healthy subjects (M = 85.1%).
SIGNIFICANCE:
The results demonstrate significant differences in electrophysiological correlates of motor control between healthy individuals and those individuals who stand to benefit most from BCI technology (individuals with SCI). They highlight the difficulty in directly translating results from healthy subjects to participants with SCI and the challenges that, therefore, arise in providing BCIs to such individuals.
2013
Daly, Ian; Sweeney-Reed, Catherine; Nasuto, Slawomir J.
Testing for significance of phase synchronisation dynamics in the EEG Journal Article
In: Journal of Computational Neuroscience, vol. 34, no. 3, pp. 411-432, 2013.
Abstract | Links | BibTeX | Tags: EEG, Functional connectivity, Markov models, Semi-Markov models, Significance testing
@article{Daly2012phase,
title = {Testing for significance of phase synchronisation dynamics in the EEG},
author = {Ian Daly and Catherine Sweeney-Reed and Slawomir J. Nasuto},
url = {http://www.iandaly.co.uk/wp-content/uploads/2016/01/Testing-for-significance-of-phase-synchronisation-dynamics-in.pdf},
doi = {10.1007/s10827-012-0428-2},
year = {2013},
date = {2013-06-01},
journal = {Journal of Computational Neuroscience},
volume = {34},
number = {3},
pages = {411-432},
abstract = {A number of tests exist to check for statistical significance of phase synchronisation within the Electroencephalogram (EEG); however, the majority suffer from a lack of generality and applicability. They may also fail to account for temporal dynamics in the phase synchronisation, regarding synchronisation as a constant state instead of a dynamical process. Therefore, a novel test is developed for identifying the statistical significance of phase synchronisation based upon a combination of work characterising temporal dynamics of multivariate time-series and Markov modelling. We show how this method is better able to assess the significance of phase synchronisation than a range of commonly used significance tests. We also show how the method may be applied to identify and classify significantly different phase synchronisation dynamics in both univariate and multivariate datasets.},
keywords = {EEG, Functional connectivity, Markov models, Semi-Markov models, Significance testing},
pubstate = {published},
tppubtype = {article}
}
A number of tests exist to check for statistical significance of phase synchronisation within the Electroencephalogram (EEG); however, the majority suffer from a lack of generality and applicability. They may also fail to account for temporal dynamics in the phase synchronisation, regarding synchronisation as a constant state instead of a dynamical process. Therefore, a novel test is developed for identifying the statistical significance of phase synchronisation based upon a combination of work characterising temporal dynamics of multivariate time-series and Markov modelling. We show how this method is better able to assess the significance of phase synchronisation than a range of commonly used significance tests. We also show how the method may be applied to identify and classify significantly different phase synchronisation dynamics in both univariate and multivariate datasets.
2012
Daly, Ian; Nasuto, Slawomir J.; Warwick, Kevin
Brain computer interface control via functional connectivity dynamics Journal Article
In: Pattern Recognition, vol. 45, no. 6, pp. 2123–2136, 2012.
Abstract | Links | BibTeX | Tags: BCI, Complex networks, Finger tapping, Functional connectivity, HMM, Phase synchronization
@article{Daly2012a,
title = {Brain computer interface control via functional connectivity dynamics},
author = {Ian Daly and Slawomir J. Nasuto and Kevin Warwick},
url = {http://www.iandaly.co.uk/wp-content/uploads/2016/01/Functional-connectivity-during-finger-taps.pdf},
doi = {10.1016/j.patcog.2011.04.034},
year = {2012},
date = {2012-06-01},
journal = {Pattern Recognition},
volume = {45},
number = {6},
pages = {2123–2136},
abstract = {The dynamics of inter-regional communication within the brain during cognitive processing – referred to as functional connectivity – are investigated as a control feature for a brain computer interface.
EMDPL is used to map phase synchronization levels between all channel pair combinations in the EEG. This results in complex networks of channel connectivity at all time–frequency locations. The mean clustering coefficient is then used as a descriptive feature encapsulating information about inter-channel connectivity.
Hidden Markov models are applied to characterize and classify dynamics of the resulting complex networks. Highly accurate levels of classification are achieved when this technique is applied to classify EEG recorded during real and imagined single finger taps. These results are compared to traditional features used in the classification of a finger tap BCI demonstrating that functional connectivity dynamics provide additional information and improved BCI control accuracies.},
keywords = {BCI, Complex networks, Finger tapping, Functional connectivity, HMM, Phase synchronization},
pubstate = {published},
tppubtype = {article}
}
The dynamics of inter-regional communication within the brain during cognitive processing – referred to as functional connectivity – are investigated as a control feature for a brain computer interface.
EMDPL is used to map phase synchronization levels between all channel pair combinations in the EEG. This results in complex networks of channel connectivity at all time–frequency locations. The mean clustering coefficient is then used as a descriptive feature encapsulating information about inter-channel connectivity.
Hidden Markov models are applied to characterize and classify dynamics of the resulting complex networks. Highly accurate levels of classification are achieved when this technique is applied to classify EEG recorded during real and imagined single finger taps. These results are compared to traditional features used in the classification of a finger tap BCI demonstrating that functional connectivity dynamics provide additional information and improved BCI control accuracies.
EMDPL is used to map phase synchronization levels between all channel pair combinations in the EEG. This results in complex networks of channel connectivity at all time–frequency locations. The mean clustering coefficient is then used as a descriptive feature encapsulating information about inter-channel connectivity.
Hidden Markov models are applied to characterize and classify dynamics of the resulting complex networks. Highly accurate levels of classification are achieved when this technique is applied to classify EEG recorded during real and imagined single finger taps. These results are compared to traditional features used in the classification of a finger tap BCI demonstrating that functional connectivity dynamics provide additional information and improved BCI control accuracies.
2011
Daly, Ian
Phase Synchronisation in Brain Computer Interfacing PhD Thesis
School of Systems Engineering, 2011.
Abstract | Links | BibTeX | Tags: Artefact removal, BCI, EEG, Feature selection, Functional connectivity, Machine learning, Neural mass models, Phase synchronisation, PhD, Significance testing, Thesis
@phdthesis{Daly2011a,
title = {Phase Synchronisation in Brain Computer Interfacing},
author = {Ian Daly},
url = {http://www.iandaly.co.uk/publications/thesis/Phase_Synchronisation_in_Brain_Computer_Interfacing.pdf},
year = {2011},
date = {2011-07-01},
pages = {1-262},
address = {University of Reading},
school = {School of Systems Engineering},
abstract = {Brain Computer Interfaces (BCIs) are an emerging area of research combining the Neuroscience, Computer Science, Engineering, Mathematics, Human Computer Interaction and Psychology research fields. A BCI enables an individual to exert control of a computer without activation of the efferent nervous system or the muscles. This allows individuals suffering with partial or complete paralysis and associated conditions which prevent muscle movement to control a computer and hence communicate and exert control over their environment.
This thesis first investigates tools for automatically removing artifacts from the Electroencephalogram (EEG), a signal commonly used in the control a BCI. Tools for measuring inter-regional connectivity patterns within the brain via phase synchronisation are then evaluated and extended to provide novel measures of inter-regional connectivity across the entire cortex.
Feature selection approaches are then introduced and evaluated before being applied to select good feature sets for the discrimination of connectivity patterns. These approaches are compared to Markov modelling approaches which model
and classify temporal dependencies in the data.
The resulting tool-set is applied to a novel BCI control paradigm based upon the detection of single finger taps. It is demonstrated that the connectivity features produce significantly better classification accuracies than can be achieved using conventional features traditionally applied in BCI.},
type = {PhD Thesis},
keywords = {Artefact removal, BCI, EEG, Feature selection, Functional connectivity, Machine learning, Neural mass models, Phase synchronisation, PhD, Significance testing, Thesis},
pubstate = {published},
tppubtype = {phdthesis}
}
Brain Computer Interfaces (BCIs) are an emerging area of research combining the Neuroscience, Computer Science, Engineering, Mathematics, Human Computer Interaction and Psychology research fields. A BCI enables an individual to exert control of a computer without activation of the efferent nervous system or the muscles. This allows individuals suffering with partial or complete paralysis and associated conditions which prevent muscle movement to control a computer and hence communicate and exert control over their environment.
This thesis first investigates tools for automatically removing artifacts from the Electroencephalogram (EEG), a signal commonly used in the control a BCI. Tools for measuring inter-regional connectivity patterns within the brain via phase synchronisation are then evaluated and extended to provide novel measures of inter-regional connectivity across the entire cortex.
Feature selection approaches are then introduced and evaluated before being applied to select good feature sets for the discrimination of connectivity patterns. These approaches are compared to Markov modelling approaches which model
and classify temporal dependencies in the data.
The resulting tool-set is applied to a novel BCI control paradigm based upon the detection of single finger taps. It is demonstrated that the connectivity features produce significantly better classification accuracies than can be achieved using conventional features traditionally applied in BCI.
This thesis first investigates tools for automatically removing artifacts from the Electroencephalogram (EEG), a signal commonly used in the control a BCI. Tools for measuring inter-regional connectivity patterns within the brain via phase synchronisation are then evaluated and extended to provide novel measures of inter-regional connectivity across the entire cortex.
Feature selection approaches are then introduced and evaluated before being applied to select good feature sets for the discrimination of connectivity patterns. These approaches are compared to Markov modelling approaches which model
and classify temporal dependencies in the data.
The resulting tool-set is applied to a novel BCI control paradigm based upon the detection of single finger taps. It is demonstrated that the connectivity features produce significantly better classification accuracies than can be achieved using conventional features traditionally applied in BCI.