Automatic ERP classification in EEG recordings from task-related independent components

Zohreh Zakeri; Mohammad Haji Samadi; Neil Cooke; Peter Jancovic

doi:10.1109/BHI.2016.7455891

Automatic ERP classification in EEG recordings from task-related independent components

Zohreh Zakeri, Mohammad Haji Samadi, Neil Cooke, Peter Jancovic

Electronic, Electrical and Systems Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

The Electroencephalography (EEG) signal contains information about a person's brain activity including the Event-Related Potential (ERP) - an evoked response to a task-related stimulus. EEG is contaminated by artefacts that degrade ERP classification performance. Independent Component Analysis (ICA) is normally employed to decompose EEG into independent components (ICs) associated to artefact and non-artefact sources. Sources identified as artefacts are removed and a cleaned EEG is reconstructed. This paper presents an alternative use of ICA for the EEG signal to extract ERP feature rather than artefact reduction. Average ERP classification accuracy increases by 15%, to 83.9%, on clinical-grade EEG data from 9 participants, when compared to similar approaches with cleaned EEG. Additionally, the proposed method obtained better performance in comparison with the state-of-the-art xDAWN method.

Original language	English
Title of host publication	IEEE Int. Conf. on Biomedical and Health Informatics
Place of Publication	USA
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	288-291
Number of pages	4
ISBN (Print)	9781509024551
DOIs	https://doi.org/10.1109/BHI.2016.7455891
Publication status	Published - 2016
Event	3rd IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2016 - Las Vegas, United States Duration: 24 Feb 2016 → 27 Feb 2016

Conference

Conference	3rd IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2016
Country/Territory	United States
City	Las Vegas
Period	24/02/16 → 27/02/16

ASJC Scopus subject areas

Health Informatics
Health Information Management

Access to Document

10.1109/BHI.2016.7455891

1 Citations
1 Paper

Object-centred recognition of human activity
Nabiei, R., Parekh, M., Jean-Baptiste, E., Jancovic, P. & Russell, M., 10 Dec 2015, (E-pub ahead of print). 6 p.
Research output: Contribution to conference (unpublished) › Paper › peer-review

File
5 Citations (Scopus)

419 Downloads (Pure)

Cite this

@inproceedings{2c005c8deed346e3aceb4f0179601aa9,

title = "Automatic ERP classification in EEG recordings from task-related independent components",

abstract = "The Electroencephalography (EEG) signal contains information about a person's brain activity including the Event-Related Potential (ERP) - an evoked response to a task-related stimulus. EEG is contaminated by artefacts that degrade ERP classification performance. Independent Component Analysis (ICA) is normally employed to decompose EEG into independent components (ICs) associated to artefact and non-artefact sources. Sources identified as artefacts are removed and a cleaned EEG is reconstructed. This paper presents an alternative use of ICA for the EEG signal to extract ERP feature rather than artefact reduction. Average ERP classification accuracy increases by 15%, to 83.9%, on clinical-grade EEG data from 9 participants, when compared to similar approaches with cleaned EEG. Additionally, the proposed method obtained better performance in comparison with the state-of-the-art xDAWN method.",

author = "Zohreh Zakeri and {Haji Samadi}, Mohammad and Neil Cooke and Peter Jancovic",

year = "2016",

doi = "10.1109/BHI.2016.7455891",

language = "English",

isbn = "9781509024551",

pages = "288--291",

booktitle = "IEEE Int. Conf. on Biomedical and Health Informatics",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

note = "3rd IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2016 ; Conference date: 24-02-2016 Through 27-02-2016",

}

Zakeri, Z, Haji Samadi, M, Cooke, N & Jancovic, P 2016, Automatic ERP classification in EEG recordings from task-related independent components. in IEEE Int. Conf. on Biomedical and Health Informatics., 7455891, Institute of Electrical and Electronics Engineers (IEEE), USA, pp. 288-291, 3rd IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2016, Las Vegas, United States, 24/02/16. https://doi.org/10.1109/BHI.2016.7455891

Automatic ERP classification in EEG recordings from task-related independent components. / Zakeri, Zohreh; Haji Samadi, Mohammad; Cooke, Neil et al.
IEEE Int. Conf. on Biomedical and Health Informatics. USA: Institute of Electrical and Electronics Engineers (IEEE), 2016. p. 288-291 7455891.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Automatic ERP classification in EEG recordings from task-related independent components

AU - Zakeri, Zohreh

AU - Haji Samadi, Mohammad

AU - Cooke, Neil

AU - Jancovic, Peter

PY - 2016

Y1 - 2016

N2 - The Electroencephalography (EEG) signal contains information about a person's brain activity including the Event-Related Potential (ERP) - an evoked response to a task-related stimulus. EEG is contaminated by artefacts that degrade ERP classification performance. Independent Component Analysis (ICA) is normally employed to decompose EEG into independent components (ICs) associated to artefact and non-artefact sources. Sources identified as artefacts are removed and a cleaned EEG is reconstructed. This paper presents an alternative use of ICA for the EEG signal to extract ERP feature rather than artefact reduction. Average ERP classification accuracy increases by 15%, to 83.9%, on clinical-grade EEG data from 9 participants, when compared to similar approaches with cleaned EEG. Additionally, the proposed method obtained better performance in comparison with the state-of-the-art xDAWN method.

AB - The Electroencephalography (EEG) signal contains information about a person's brain activity including the Event-Related Potential (ERP) - an evoked response to a task-related stimulus. EEG is contaminated by artefacts that degrade ERP classification performance. Independent Component Analysis (ICA) is normally employed to decompose EEG into independent components (ICs) associated to artefact and non-artefact sources. Sources identified as artefacts are removed and a cleaned EEG is reconstructed. This paper presents an alternative use of ICA for the EEG signal to extract ERP feature rather than artefact reduction. Average ERP classification accuracy increases by 15%, to 83.9%, on clinical-grade EEG data from 9 participants, when compared to similar approaches with cleaned EEG. Additionally, the proposed method obtained better performance in comparison with the state-of-the-art xDAWN method.

UR - http://www.scopus.com/inward/record.url?scp=84968547890&partnerID=8YFLogxK

U2 - 10.1109/BHI.2016.7455891

DO - 10.1109/BHI.2016.7455891

M3 - Conference contribution

AN - SCOPUS:84968547890

SN - 9781509024551

SP - 288

EP - 291

BT - IEEE Int. Conf. on Biomedical and Health Informatics

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - USA

T2 - 3rd IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2016

Y2 - 24 February 2016 through 27 February 2016

ER -

Automatic ERP classification in EEG recordings from task-related independent components

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Fingerprint

Research output

Object-centred recognition of human activity

Cite this