A Study on Mental State Classification using EEG-based Brain-Machine Interface

Jordan Bird, Luis J. Manso, Eduardo P. Ribeiro, Anikó Ekárt, Diego Faria

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

Abstract

This work aims to find discriminative EEG-based features and appropriate classification methods that can categorise brainwave patterns based on their level of activity or frequency for mental state recognition useful for human-machine interaction. By using the Muse headband with four EEG sensors (TP9, AF7, AF8, TP10), we categorised three possible states such as relaxing, neutral and concentrating based on a few states of mind defined by cognitive behavioural studies. We have created a dataset with five individuals and sessions lasting one minute for each class of mental state in order to train and test different methods. Given the proposed set of features extracted from the EEG headband five signals (alpha, beta, theta, delta, gamma), we have tested a combination of different features selection algorithms and classifier models to compare their performance in terms of recognition accuracy and number of features needed. Different tests such as 10-fold cross validation were performed. Results show that only 44 features from a set of over 2100 features are necessary when used with classical classifiers such as Bayesian Networks, Support Vector Machines and Random Forests, attaining an overall accuracy over 87%.
Original languageEnglish
Title of host publication9th International Conference on Intelligent Systems 2018
Subtitle of host publicationTheory, Research and Innovation in Applications, IS 2018 - Proceedings
EditorsJoao Martins, Vladimir Jotsov, Robert Bierwolf, Joao Pedro Mendonca, Ricardo Jardim-Goncalves, Maria Marques
PublisherIEEE
Pages795-800
Number of pages6
ISBN (Electronic)978-1-5386-7097-2
ISBN (Print)978-1-5386-7097-2
DOIs
Publication statusPublished - 8 May 2019
Event9th international Conference on Intelligent Systems 2018
- Madeira Island, Portugal
Duration: 25 Sep 201827 Sep 2018

Publication series

Name2018 International Conference on Intelligent Systems (IS)
PublisherIEEE
ISSN (Print)1541-1672

Conference

Conference9th international Conference on Intelligent Systems 2018
CountryPortugal
CityMadeira Island
Period25/09/1827/09/18

Fingerprint

Electroencephalography
Brain
Classifiers
Bayesian networks
Support vector machines
Feature extraction
Sensors

Keywords

  • Brain-machine interface
  • EEG
  • Machine learning
  • Mental states classification

Cite this

Bird, J., Manso, L. J., Ribeiro, E. P., Ekárt, A., & Faria, D. (2019). A Study on Mental State Classification using EEG-based Brain-Machine Interface. In J. Martins, V. Jotsov, R. Bierwolf, J. P. Mendonca, R. Jardim-Goncalves, & M. Marques (Eds.), 9th International Conference on Intelligent Systems 2018: Theory, Research and Innovation in Applications, IS 2018 - Proceedings (pp. 795-800). [8710576] (2018 International Conference on Intelligent Systems (IS)). IEEE. https://doi.org/10.1109/IS.2018.8710576
Bird, Jordan ; Manso, Luis J. ; Ribeiro, Eduardo P. ; Ekárt, Anikó ; Faria, Diego. / A Study on Mental State Classification using EEG-based Brain-Machine Interface. 9th International Conference on Intelligent Systems 2018: Theory, Research and Innovation in Applications, IS 2018 - Proceedings. editor / Joao Martins ; Vladimir Jotsov ; Robert Bierwolf ; Joao Pedro Mendonca ; Ricardo Jardim-Goncalves ; Maria Marques. IEEE, 2019. pp. 795-800 (2018 International Conference on Intelligent Systems (IS)).
@inproceedings{433e82f790304d179d56a7426a662219,
title = "A Study on Mental State Classification using EEG-based Brain-Machine Interface",
abstract = "This work aims to find discriminative EEG-based features and appropriate classification methods that can categorise brainwave patterns based on their level of activity or frequency for mental state recognition useful for human-machine interaction. By using the Muse headband with four EEG sensors (TP9, AF7, AF8, TP10), we categorised three possible states such as relaxing, neutral and concentrating based on a few states of mind defined by cognitive behavioural studies. We have created a dataset with five individuals and sessions lasting one minute for each class of mental state in order to train and test different methods. Given the proposed set of features extracted from the EEG headband five signals (alpha, beta, theta, delta, gamma), we have tested a combination of different features selection algorithms and classifier models to compare their performance in terms of recognition accuracy and number of features needed. Different tests such as 10-fold cross validation were performed. Results show that only 44 features from a set of over 2100 features are necessary when used with classical classifiers such as Bayesian Networks, Support Vector Machines and Random Forests, attaining an overall accuracy over 87{\%}.",
keywords = "Brain-machine interface, EEG, Machine learning, Mental states classification",
author = "Jordan Bird and Manso, {Luis J.} and Ribeiro, {Eduardo P.} and Anik{\'o} Ek{\'a}rt and Diego Faria",
year = "2019",
month = "5",
day = "8",
doi = "10.1109/IS.2018.8710576",
language = "English",
isbn = "978-1-5386-7097-2",
series = "2018 International Conference on Intelligent Systems (IS)",
publisher = "IEEE",
pages = "795--800",
editor = "Joao Martins and Vladimir Jotsov and Robert Bierwolf and Mendonca, {Joao Pedro} and Ricardo Jardim-Goncalves and Maria Marques",
booktitle = "9th International Conference on Intelligent Systems 2018",
address = "United States",

}

Bird, J, Manso, LJ, Ribeiro, EP, Ekárt, A & Faria, D 2019, A Study on Mental State Classification using EEG-based Brain-Machine Interface. in J Martins, V Jotsov, R Bierwolf, JP Mendonca, R Jardim-Goncalves & M Marques (eds), 9th International Conference on Intelligent Systems 2018: Theory, Research and Innovation in Applications, IS 2018 - Proceedings., 8710576, 2018 International Conference on Intelligent Systems (IS), IEEE, pp. 795-800, 9th international Conference on Intelligent Systems 2018
, Madeira Island, Portugal, 25/09/18. https://doi.org/10.1109/IS.2018.8710576

A Study on Mental State Classification using EEG-based Brain-Machine Interface. / Bird, Jordan; Manso, Luis J.; Ribeiro, Eduardo P.; Ekárt, Anikó; Faria, Diego.

9th International Conference on Intelligent Systems 2018: Theory, Research and Innovation in Applications, IS 2018 - Proceedings. ed. / Joao Martins; Vladimir Jotsov; Robert Bierwolf; Joao Pedro Mendonca; Ricardo Jardim-Goncalves; Maria Marques. IEEE, 2019. p. 795-800 8710576 (2018 International Conference on Intelligent Systems (IS)).

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

TY - GEN

T1 - A Study on Mental State Classification using EEG-based Brain-Machine Interface

AU - Bird, Jordan

AU - Manso, Luis J.

AU - Ribeiro, Eduardo P.

AU - Ekárt, Anikó

AU - Faria, Diego

PY - 2019/5/8

Y1 - 2019/5/8

N2 - This work aims to find discriminative EEG-based features and appropriate classification methods that can categorise brainwave patterns based on their level of activity or frequency for mental state recognition useful for human-machine interaction. By using the Muse headband with four EEG sensors (TP9, AF7, AF8, TP10), we categorised three possible states such as relaxing, neutral and concentrating based on a few states of mind defined by cognitive behavioural studies. We have created a dataset with five individuals and sessions lasting one minute for each class of mental state in order to train and test different methods. Given the proposed set of features extracted from the EEG headband five signals (alpha, beta, theta, delta, gamma), we have tested a combination of different features selection algorithms and classifier models to compare their performance in terms of recognition accuracy and number of features needed. Different tests such as 10-fold cross validation were performed. Results show that only 44 features from a set of over 2100 features are necessary when used with classical classifiers such as Bayesian Networks, Support Vector Machines and Random Forests, attaining an overall accuracy over 87%.

AB - This work aims to find discriminative EEG-based features and appropriate classification methods that can categorise brainwave patterns based on their level of activity or frequency for mental state recognition useful for human-machine interaction. By using the Muse headband with four EEG sensors (TP9, AF7, AF8, TP10), we categorised three possible states such as relaxing, neutral and concentrating based on a few states of mind defined by cognitive behavioural studies. We have created a dataset with five individuals and sessions lasting one minute for each class of mental state in order to train and test different methods. Given the proposed set of features extracted from the EEG headband five signals (alpha, beta, theta, delta, gamma), we have tested a combination of different features selection algorithms and classifier models to compare their performance in terms of recognition accuracy and number of features needed. Different tests such as 10-fold cross validation were performed. Results show that only 44 features from a set of over 2100 features are necessary when used with classical classifiers such as Bayesian Networks, Support Vector Machines and Random Forests, attaining an overall accuracy over 87%.

KW - Brain-machine interface

KW - EEG

KW - Machine learning

KW - Mental states classification

UR - https://ieeexplore.ieee.org/document/8710576

UR - http://www.scopus.com/inward/record.url?scp=85064401535&partnerID=8YFLogxK

U2 - 10.1109/IS.2018.8710576

DO - 10.1109/IS.2018.8710576

M3 - Conference contribution

SN - 978-1-5386-7097-2

T3 - 2018 International Conference on Intelligent Systems (IS)

SP - 795

EP - 800

BT - 9th International Conference on Intelligent Systems 2018

A2 - Martins, Joao

A2 - Jotsov, Vladimir

A2 - Bierwolf, Robert

A2 - Mendonca, Joao Pedro

A2 - Jardim-Goncalves, Ricardo

A2 - Marques, Maria

PB - IEEE

ER -

Bird J, Manso LJ, Ribeiro EP, Ekárt A, Faria D. A Study on Mental State Classification using EEG-based Brain-Machine Interface. In Martins J, Jotsov V, Bierwolf R, Mendonca JP, Jardim-Goncalves R, Marques M, editors, 9th International Conference on Intelligent Systems 2018: Theory, Research and Innovation in Applications, IS 2018 - Proceedings. IEEE. 2019. p. 795-800. 8710576. (2018 International Conference on Intelligent Systems (IS)). https://doi.org/10.1109/IS.2018.8710576