Publications
2022
Fang, Hua; Jin, Jing; Daly, Ian; yu Wang, Xing
Feature Extraction Method Based on Filter Banks and Riemannian Tangent Space in Motor-Imagery BCI Journal Article
In: IEEE Journal of Biomedical and Health Informatics, 2022.
Links | BibTeX | Tags: BCI, EEG, Feature selection, Machine learning
@article{Fang2022,
title = {Feature Extraction Method Based on Filter Banks and Riemannian Tangent Space in Motor-Imagery BCI},
author = {Hua Fang and Jing Jin and Ian Daly and Xing yu Wang},
doi = {10.1109/JBHI.2022.3146274},
year = {2022},
date = {2022-01-31},
journal = {IEEE Journal of Biomedical and Health Informatics},
keywords = {BCI, EEG, Feature selection, Machine learning},
pubstate = {published},
tppubtype = {article}
}
2021
Li, Shurui; Jin, Jing; Daly, Ian; Liu, Chang; Cichocki, Andrzej
Feature Selection method based on Menger Curvature and LDA Theory for a P300 Brain-computer Interface Journal Article
In: Journal of Neural Engineering, 2021.
BibTeX | Tags: BCI, EEG, Feature selection
@article{Li2021Menger,
title = {Feature Selection method based on Menger Curvature and LDA Theory for a P300 Brain-computer Interface},
author = {Shurui Li and Jing Jin and Ian Daly and Chang Liu and Andrzej Cichocki},
year = {2021},
date = {2021-11-29},
journal = {Journal of Neural Engineering},
keywords = {BCI, EEG, Feature selection},
pubstate = {published},
tppubtype = {article}
}
Torres, Juan Ramirez; Daly, Ian
How to build a fast and accurate Code-Modulated Brain-Computer Interface Journal Article
In: Journal of Neural Engineering, 2021.
BibTeX | Tags: BCI, Classification, cVEP, EEG, ERP, Event-related potential, Feature selection
@article{Ramirez-Torres2021,
title = {How to build a fast and accurate Code-Modulated Brain-Computer Interface},
author = {Juan Ramirez Torres and Ian Daly},
year = {2021},
date = {2021-04-21},
journal = {Journal of Neural Engineering},
keywords = {BCI, Classification, cVEP, EEG, ERP, Event-related potential, Feature selection},
pubstate = {published},
tppubtype = {article}
}
2020
Daly, Ian
Neural component analysis: a spatial filter for electroencephalogram analysis Journal Article
In: Journal of Neuroscience Methods, 2020.
BibTeX | Tags: Classification, EEG, ERP, Event-related potential, Feature selection, Machine learning
@article{Daly2020NCA,
title = {Neural component analysis: a spatial filter for electroencephalogram analysis},
author = {Ian Daly},
year = {2020},
date = {2020-10-20},
journal = {Journal of Neuroscience Methods},
keywords = {Classification, EEG, ERP, Event-related potential, Feature selection, Machine learning},
pubstate = {published},
tppubtype = {article}
}
Jin, Jing; Liu, Chang; Daly, Ian; Miao, Yangyang; Li, Shurui; Wang, Xingyu; Cichocki, Andrzej
Bispectrum-based Channel Selection for Motor Imagery based Brain-Computer Interfacing Journal Article
In: IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2020.
Links | BibTeX | Tags: BCI, Classification, Feature selection, Motor imagery
@article{Jin2020bispectrum,
title = {Bispectrum-based Channel Selection for Motor Imagery based Brain-Computer Interfacing},
author = {Jing Jin and Chang Liu and Ian Daly and Yangyang Miao and Shurui Li and Xingyu Wang and Andrzej Cichocki},
doi = {10.1109/TNSRE.2020.3020975},
year = {2020},
date = {2020-09-01},
journal = {IEEE Transactions on Neural Systems and Rehabilitation Engineering},
keywords = {BCI, Classification, Feature selection, Motor imagery},
pubstate = {published},
tppubtype = {article}
}
2019
Jin, Jing; Miao, Yangyang; Daly, Ian; Zuo, Cili; Hu, Dewen; Cichocki, Andrzej
Correlation-based channel selection and regularized feature optimization for MI-based BCI Journal Article
In: Neural Networks, 2019.
Links | BibTeX | Tags: BCI, Channel selection, EEG, Feature selection, Machine learning, Motor imagery
@article{Jin2019NN,
title = {Correlation-based channel selection and regularized feature optimization for MI-based BCI},
author = {Jing Jin and Yangyang Miao and Ian Daly and Cili Zuo and Dewen Hu and Andrzej Cichocki},
url = {https://www.sciencedirect.com/science/article/pii/S0893608019301960?dgcid=coauthor},
doi = {https://doi.org/10.1016/j.neunet.2019.07.008},
year = {2019},
date = {2019-07-15},
journal = {Neural Networks},
keywords = {BCI, Channel selection, EEG, Feature selection, Machine learning, Motor imagery},
pubstate = {published},
tppubtype = {article}
}
Feng, Jiankui; Jin, Jing; Daly, Ian; Zhou, Jiale; Niu, Yugang; Wang, Xingyu; Cichocki, Andrzej
An Optimized Channel Selection Method based on Multi-frequency CSP-rank for Motor Imagery-based BCI system Journal Article
In: Computational Intelligence and Neuroscience, 2019.
BibTeX | Tags: BCI, Feature selection, Machine learning, Motor imagery
@article{Feng2019,
title = {An Optimized Channel Selection Method based on Multi-frequency CSP-rank for Motor Imagery-based BCI system},
author = {Jiankui Feng and Jing Jin and Ian Daly and Jiale Zhou and Yugang Niu and Xingyu Wang and Andrzej Cichocki},
year = {2019},
date = {2019-04-18},
journal = {Computational Intelligence and Neuroscience},
keywords = {BCI, Feature selection, Machine learning, Motor imagery},
pubstate = {published},
tppubtype = {article}
}
2017
Daly, Ian; Williams, Duncan; Malik, Asad; Weaver, James; Kirke, Alexis; Hwang, Faustina; Miranda, Eduardo; Nasuto, Slawomir J.
Personalised, Multi-modal, Affective State Detection for Hybrid Brain-Computer Music Interfacing Journal Article
In: IEEE Transactions on Affective Computing, 2017.
Abstract | BibTeX | Tags: Affective computing, BCI, Classification, Feature selection, Machine learning
@article{Daly2017b,
title = {Personalised, Multi-modal, Affective State Detection for Hybrid Brain-Computer Music Interfacing},
author = {Ian Daly and Duncan Williams and Asad Malik and James Weaver and Alexis Kirke and Faustina Hwang and Eduardo Miranda and Slawomir J. Nasuto},
year = {2017},
date = {2017-10-08},
journal = {IEEE Transactions on Affective Computing},
abstract = {Brain-computer music interfaces (BCMIs) may be used to modulate affective states, with applications in music therapy, composition, and entertainment. However, for such systems to work they need to be able to reliably detect their user’s current affective state.
We present a method for personalised affective state detection for use in BCMI. We compare it to a population-based detection method trained on 17 users and demonstrate that personalised affective state detection is significantly (p < 0:01) more accurate, with average improvements in accuracy of 10.2% for valence and 9.3% for arousal. We also compare a hybrid BCMI (a BCMI that combines physiological signals with neurological signals) to a conventional BCMI design
one based upon the use of only EEG features) and demonstrate that the hybrid design results in a significant (p < 0:01) 6.2% improvement in performance for arousal classification and a significant (p < 0:01) 5.9% improvement for valence classification.},
keywords = {Affective computing, BCI, Classification, Feature selection, Machine learning},
pubstate = {published},
tppubtype = {article}
}
Brain-computer music interfaces (BCMIs) may be used to modulate affective states, with applications in music therapy, composition, and entertainment. However, for such systems to work they need to be able to reliably detect their user’s current affective state.
We present a method for personalised affective state detection for use in BCMI. We compare it to a population-based detection method trained on 17 users and demonstrate that personalised affective state detection is significantly (p < 0:01) more accurate, with average improvements in accuracy of 10.2% for valence and 9.3% for arousal. We also compare a hybrid BCMI (a BCMI that combines physiological signals with neurological signals) to a conventional BCMI design
one based upon the use of only EEG features) and demonstrate that the hybrid design results in a significant (p < 0:01) 6.2% improvement in performance for arousal classification and a significant (p < 0:01) 5.9% improvement for valence classification.
We present a method for personalised affective state detection for use in BCMI. We compare it to a population-based detection method trained on 17 users and demonstrate that personalised affective state detection is significantly (p < 0:01) more accurate, with average improvements in accuracy of 10.2% for valence and 9.3% for arousal. We also compare a hybrid BCMI (a BCMI that combines physiological signals with neurological signals) to a conventional BCMI design
one based upon the use of only EEG features) and demonstrate that the hybrid design results in a significant (p < 0:01) 6.2% improvement in performance for arousal classification and a significant (p < 0:01) 5.9% improvement for valence classification.
2015
Daly, Ian; Hwang, Faustina; Kirke, Alexis; Malik, Asad; Weaver, James; Williams, Duncan; Miranda, Eduardo; Nasuto, Slawomir
Automated identification of neural correlates of continuous variables Journal Article
In: Journal of Neuroscience Methods, vol. 242, pp. 65–71, 2015.
Abstract | Links | BibTeX | Tags: EEG, Feature selection
@article{Daly2014_featSel,
title = {Automated identification of neural correlates of continuous variables},
author = {Ian Daly and Faustina Hwang and Alexis Kirke and Asad Malik and James Weaver and Duncan Williams and Eduardo Miranda and Slawomir Nasuto},
url = {http://www.iandaly.co.uk/wp-content/uploads/2016/01/Automated-identification-of-neural-correlates-of-continous-variables.pdf},
doi = {10.1016/j.jneumeth.2014.12.012},
year = {2015},
date = {2015-03-15},
journal = {Journal of Neuroscience Methods},
volume = {242},
pages = { 65–71},
abstract = {Background
The electroencephalogram (EEG) may be described by a large number of different feature types and automated feature selection methods are needed in order to reliably identify features which correlate with continuous independent variables.
New method
A method is presented for the automated identification of features that differentiate two or more groups in neurological datasets based upon a spectral decomposition of the feature set. Furthermore, the method is able to identify features that relate to continuous independent variables.
Results
The proposed method is first evaluated on synthetic EEG datasets and observed to reliably identify the correct features. The method is then applied to EEG recorded during a music listening task and is observed to automatically identify neural correlates of music tempo changes similar to neural correlates identified in a previous study. Finally, the method is applied to identify neural correlates of music-induced affective states. The identified neural correlates reside primarily over the frontal cortex and are consistent with widely reported neural correlates of emotions.
Comparison with existing methods
The proposed method is compared to the state-of-the-art methods of canonical correlation analysis and common spatial patterns, in order to identify features differentiating synthetic event-related potentials of different amplitudes and is observed to exhibit greater performance as the number of unique groups in the dataset increases.
Conclusions
The proposed method is able to identify neural correlates of continuous variables in EEG datasets and is shown to outperform canonical correlation analysis and common spatial patterns.},
keywords = {EEG, Feature selection},
pubstate = {published},
tppubtype = {article}
}
Background
The electroencephalogram (EEG) may be described by a large number of different feature types and automated feature selection methods are needed in order to reliably identify features which correlate with continuous independent variables.
New method
A method is presented for the automated identification of features that differentiate two or more groups in neurological datasets based upon a spectral decomposition of the feature set. Furthermore, the method is able to identify features that relate to continuous independent variables.
Results
The proposed method is first evaluated on synthetic EEG datasets and observed to reliably identify the correct features. The method is then applied to EEG recorded during a music listening task and is observed to automatically identify neural correlates of music tempo changes similar to neural correlates identified in a previous study. Finally, the method is applied to identify neural correlates of music-induced affective states. The identified neural correlates reside primarily over the frontal cortex and are consistent with widely reported neural correlates of emotions.
Comparison with existing methods
The proposed method is compared to the state-of-the-art methods of canonical correlation analysis and common spatial patterns, in order to identify features differentiating synthetic event-related potentials of different amplitudes and is observed to exhibit greater performance as the number of unique groups in the dataset increases.
Conclusions
The proposed method is able to identify neural correlates of continuous variables in EEG datasets and is shown to outperform canonical correlation analysis and common spatial patterns.
The electroencephalogram (EEG) may be described by a large number of different feature types and automated feature selection methods are needed in order to reliably identify features which correlate with continuous independent variables.
New method
A method is presented for the automated identification of features that differentiate two or more groups in neurological datasets based upon a spectral decomposition of the feature set. Furthermore, the method is able to identify features that relate to continuous independent variables.
Results
The proposed method is first evaluated on synthetic EEG datasets and observed to reliably identify the correct features. The method is then applied to EEG recorded during a music listening task and is observed to automatically identify neural correlates of music tempo changes similar to neural correlates identified in a previous study. Finally, the method is applied to identify neural correlates of music-induced affective states. The identified neural correlates reside primarily over the frontal cortex and are consistent with widely reported neural correlates of emotions.
Comparison with existing methods
The proposed method is compared to the state-of-the-art methods of canonical correlation analysis and common spatial patterns, in order to identify features differentiating synthetic event-related potentials of different amplitudes and is observed to exhibit greater performance as the number of unique groups in the dataset increases.
Conclusions
The proposed method is able to identify neural correlates of continuous variables in EEG datasets and is shown to outperform canonical correlation analysis and common spatial patterns.
2014
Singh, Harsimrat; Daly, Ian
Translational Algorithms: the heart of a Brain Computer Interface Book Chapter
In: Aboul Ella Hassanien, Ahmad Taher Azar (Ed.): vol. 74, pp. 97-121, Springer, 2014, ISBN: 978-3-319-10977-0.
Abstract | Links | BibTeX | Tags: BCI classification, Event related (de)/synchronisation, Feature extraction, Feature selection, Principal component analysis
@inbook{SinghDaly2015,
title = {Translational Algorithms: the heart of a Brain Computer Interface},
author = {Harsimrat Singh and Ian Daly},
editor = {Aboul Ella Hassanien, Ahmad Taher Azar},
url = {http://www.iandaly.co.uk/wp-content/uploads/2016/01/Translational-Algorithms-the-heart-of-a-Brain-computer-Interface.pdf},
doi = {10.1007/978-3-319-10978-7_4},
isbn = {978-3-319-10977-0},
year = {2014},
date = {2014-11-02},
volume = {74},
pages = {97-121},
publisher = {Springer},
abstract = {Brain computer Interface (BCI) development encapsulates three basic processes: data acquisition, data processing, and device control. Since the start of the millennium the BCI development cycle has undergone a metamorphosis. This is mainly due to the increased popularity of BCI applications in both commercial and research circles. One of the focuses of BCI research is to bridge the gap between laboratory research and commercial applications using this technology. A vast variety of new approaches are being employed for BCI development ranging from novel paradigms, such as simultaneous acquisitions, through to asynchronous BCI control. The strategic usage of computational techniques, comprising the heart of the BCI system, underwrites this vast range of approaches. This chapter discusses these computational strategies and translational techniques including dimensionality reduction, feature extraction, feature selection, and classification techniques.},
keywords = {BCI classification, Event related (de)/synchronisation, Feature extraction, Feature selection, Principal component analysis},
pubstate = {published},
tppubtype = {inbook}
}
Brain computer Interface (BCI) development encapsulates three basic processes: data acquisition, data processing, and device control. Since the start of the millennium the BCI development cycle has undergone a metamorphosis. This is mainly due to the increased popularity of BCI applications in both commercial and research circles. One of the focuses of BCI research is to bridge the gap between laboratory research and commercial applications using this technology. A vast variety of new approaches are being employed for BCI development ranging from novel paradigms, such as simultaneous acquisitions, through to asynchronous BCI control. The strategic usage of computational techniques, comprising the heart of the BCI system, underwrites this vast range of approaches. This chapter discusses these computational strategies and translational techniques including dimensionality reduction, feature extraction, feature selection, and classification techniques.
2013
Daly, Ian; Scherer, Reinhold; Müller-Putz, Gernot
A population search algorithm for multiple clustered solutions: application to EEG connectivity Conference
Proceedings of BiomMed 2013, 2013.
BibTeX | Tags: EEG, Feature selection, Machine learning, Population search
@conference{Daly2013,
title = {A population search algorithm for multiple clustered solutions: application to EEG connectivity},
author = {Ian Daly and Reinhold Scherer and Gernot Müller-Putz},
year = {2013},
date = {2013-11-01},
booktitle = {Proceedings of BiomMed 2013},
keywords = {EEG, Feature selection, Machine learning, Population search},
pubstate = {published},
tppubtype = {conference}
}
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.