A Hybrid ICA-Wavelet Transform for Automated Artefact Removal in EEG-based Emotion Recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Removing artefacts from electroencephalographic (EEG) recordings normally increases their low signal-to-noise ratio and enables more reliable interpretation of brain activity. In this paper we present an evaluation of an automatic independent component analysis (ICA) procedure, a hybrid ICA - wavelet transform technique (ICA-W), for artefact removal from EEG correlated to emotional-state. Spectral and statistical features were classified with support vector machines (SVM) to assess the performance of ICA-W against the regular ICA, in terms of the accuracy of classifying emotional states from EEG. Accuracies on data from 14 subjects are reported and the results indicate that ICA-W performs better than traditional ICA in statistical and wavelet based features whilst the best overall performance is achieved when combining ICA-W with statistical features with an average accuracy across subjects of 74.11% for classifying four categories of emotion. ICA-W is therefore demonstrated to enhance EEG-based emotion recognition applications in terms of performance and ease of application.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages4429-4434
Number of pages6
DOIs
Publication statusPublished - 9 Oct 2016
Event2016 IEEE International Conference on Systems, Man, and Cybernetics - Budapest, Hungary
Duration: 9 Oct 2016 → …

Conference

Conference2016 IEEE International Conference on Systems, Man, and Cybernetics
Period9/10/16 → …

Fingerprint

Independent component analysis
Wavelet transforms
Support vector machines
Brain
Signal to noise ratio

Keywords

  • Independent component analysis
  • EEG
  • wavelet
  • emotion

Cite this

@inproceedings{3ae2f0c6edc546aa96401243388b211e,
title = "A Hybrid ICA-Wavelet Transform for Automated Artefact Removal in EEG-based Emotion Recognition",
abstract = "Removing artefacts from electroencephalographic (EEG) recordings normally increases their low signal-to-noise ratio and enables more reliable interpretation of brain activity. In this paper we present an evaluation of an automatic independent component analysis (ICA) procedure, a hybrid ICA - wavelet transform technique (ICA-W), for artefact removal from EEG correlated to emotional-state. Spectral and statistical features were classified with support vector machines (SVM) to assess the performance of ICA-W against the regular ICA, in terms of the accuracy of classifying emotional states from EEG. Accuracies on data from 14 subjects are reported and the results indicate that ICA-W performs better than traditional ICA in statistical and wavelet based features whilst the best overall performance is achieved when combining ICA-W with statistical features with an average accuracy across subjects of 74.11{\%} for classifying four categories of emotion. ICA-W is therefore demonstrated to enhance EEG-based emotion recognition applications in terms of performance and ease of application.",
keywords = "Independent component analysis, EEG, wavelet, emotion",
author = "Alain Bigirimana and Nazmul Siddique and Damien Coyle",
year = "2016",
month = "10",
day = "9",
doi = "10.1109/SMC.2016.7844928",
language = "English",
isbn = "978-1-5090-1897-0",
pages = "4429--4434",
booktitle = "Unknown Host Publication",

}

Bigirimana, A, Siddique, N & Coyle, D 2016, A Hybrid ICA-Wavelet Transform for Automated Artefact Removal in EEG-based Emotion Recognition. in Unknown Host Publication. pp. 4429-4434, 2016 IEEE International Conference on Systems, Man, and Cybernetics, 9/10/16. https://doi.org/10.1109/SMC.2016.7844928

A Hybrid ICA-Wavelet Transform for Automated Artefact Removal in EEG-based Emotion Recognition. / Bigirimana, Alain; Siddique, Nazmul; Coyle, Damien.

Unknown Host Publication. 2016. p. 4429-4434.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A Hybrid ICA-Wavelet Transform for Automated Artefact Removal in EEG-based Emotion Recognition

AU - Bigirimana, Alain

AU - Siddique, Nazmul

AU - Coyle, Damien

PY - 2016/10/9

Y1 - 2016/10/9

N2 - Removing artefacts from electroencephalographic (EEG) recordings normally increases their low signal-to-noise ratio and enables more reliable interpretation of brain activity. In this paper we present an evaluation of an automatic independent component analysis (ICA) procedure, a hybrid ICA - wavelet transform technique (ICA-W), for artefact removal from EEG correlated to emotional-state. Spectral and statistical features were classified with support vector machines (SVM) to assess the performance of ICA-W against the regular ICA, in terms of the accuracy of classifying emotional states from EEG. Accuracies on data from 14 subjects are reported and the results indicate that ICA-W performs better than traditional ICA in statistical and wavelet based features whilst the best overall performance is achieved when combining ICA-W with statistical features with an average accuracy across subjects of 74.11% for classifying four categories of emotion. ICA-W is therefore demonstrated to enhance EEG-based emotion recognition applications in terms of performance and ease of application.

AB - Removing artefacts from electroencephalographic (EEG) recordings normally increases their low signal-to-noise ratio and enables more reliable interpretation of brain activity. In this paper we present an evaluation of an automatic independent component analysis (ICA) procedure, a hybrid ICA - wavelet transform technique (ICA-W), for artefact removal from EEG correlated to emotional-state. Spectral and statistical features were classified with support vector machines (SVM) to assess the performance of ICA-W against the regular ICA, in terms of the accuracy of classifying emotional states from EEG. Accuracies on data from 14 subjects are reported and the results indicate that ICA-W performs better than traditional ICA in statistical and wavelet based features whilst the best overall performance is achieved when combining ICA-W with statistical features with an average accuracy across subjects of 74.11% for classifying four categories of emotion. ICA-W is therefore demonstrated to enhance EEG-based emotion recognition applications in terms of performance and ease of application.

KW - Independent component analysis

KW - EEG

KW - wavelet

KW - emotion

U2 - 10.1109/SMC.2016.7844928

DO - 10.1109/SMC.2016.7844928

M3 - Conference contribution

SN - 978-1-5090-1897-0

SP - 4429

EP - 4434

BT - Unknown Host Publication

ER -