Development of a brain computer interface interface using multi-frequency visual stimulation and deep neural networks

Research output: Contribution to conferencePaperResearch

Abstract

© 2018 IEEE. This work proposes a Brain Computer Interface based on using multi-frequency visual stimulation and deep neural networks for signals classification. The use of multi-frequency stimulation, combined with a new proposed coding method codifying up to 220 commands, which could be used to create a large multi-command brain computer interface. The advantages this method for commands codification and classification performance is analyzed in a five commands Brain computer interface. The classification of the electroencephalographic signals used in the interface was performed using several algorithms. The outcomes reveal that the best classification algorithm is a deep neural network, which gives a classification accuracy of 97.78 %. This algorithm, also, allows establishing the most relevant features of the electroencephalographic signal spectrums for the classification and information extraction from the evoked potentials.
Original languageAmerican English
Pages18-24
Number of pages15
DOIs
StatePublished - 27 Mar 2018
Event2018 28th International Conference on Electronics, Communications and Computers, CONIELECOMP 2018 -
Duration: 27 Mar 2018 → …

Conference

Conference2018 28th International Conference on Electronics, Communications and Computers, CONIELECOMP 2018
Period27/03/18 → …

Fingerprint

Brain computer interface
Bioelectric potentials
Deep neural networks

Cite this

Perez-Benitez, J. L., Perez-Benitez, J. A., & Espina-Hernandez, J. H. (2018). Development of a brain computer interface interface using multi-frequency visual stimulation and deep neural networks. 18-24. Paper presented at 2018 28th International Conference on Electronics, Communications and Computers, CONIELECOMP 2018, . https://doi.org/10.1109/CONIELECOMP.2018.8327170
Perez-Benitez, J. L. ; Perez-Benitez, J. A. ; Espina-Hernandez, J. H. / Development of a brain computer interface interface using multi-frequency visual stimulation and deep neural networks. Paper presented at 2018 28th International Conference on Electronics, Communications and Computers, CONIELECOMP 2018, .15 p.
@conference{9380319ea73e484aaf312ed26aff4b4f,
title = "Development of a brain computer interface interface using multi-frequency visual stimulation and deep neural networks",
abstract = "{\circledC} 2018 IEEE. This work proposes a Brain Computer Interface based on using multi-frequency visual stimulation and deep neural networks for signals classification. The use of multi-frequency stimulation, combined with a new proposed coding method codifying up to 220 commands, which could be used to create a large multi-command brain computer interface. The advantages this method for commands codification and classification performance is analyzed in a five commands Brain computer interface. The classification of the electroencephalographic signals used in the interface was performed using several algorithms. The outcomes reveal that the best classification algorithm is a deep neural network, which gives a classification accuracy of 97.78 {\%}. This algorithm, also, allows establishing the most relevant features of the electroencephalographic signal spectrums for the classification and information extraction from the evoked potentials.",
author = "Perez-Benitez, {J. L.} and Perez-Benitez, {J. A.} and Espina-Hernandez, {J. H.}",
year = "2018",
month = "3",
day = "27",
doi = "10.1109/CONIELECOMP.2018.8327170",
language = "American English",
pages = "18--24",
note = "2018 28th International Conference on Electronics, Communications and Computers, CONIELECOMP 2018 ; Conference date: 27-03-2018",

}

Perez-Benitez, JL, Perez-Benitez, JA & Espina-Hernandez, JH 2018, 'Development of a brain computer interface interface using multi-frequency visual stimulation and deep neural networks' Paper presented at 2018 28th International Conference on Electronics, Communications and Computers, CONIELECOMP 2018, 27/03/18, pp. 18-24. https://doi.org/10.1109/CONIELECOMP.2018.8327170

Development of a brain computer interface interface using multi-frequency visual stimulation and deep neural networks. / Perez-Benitez, J. L.; Perez-Benitez, J. A.; Espina-Hernandez, J. H.

2018. 18-24 Paper presented at 2018 28th International Conference on Electronics, Communications and Computers, CONIELECOMP 2018, .

Research output: Contribution to conferencePaperResearch

TY - CONF

T1 - Development of a brain computer interface interface using multi-frequency visual stimulation and deep neural networks

AU - Perez-Benitez, J. L.

AU - Perez-Benitez, J. A.

AU - Espina-Hernandez, J. H.

PY - 2018/3/27

Y1 - 2018/3/27

N2 - © 2018 IEEE. This work proposes a Brain Computer Interface based on using multi-frequency visual stimulation and deep neural networks for signals classification. The use of multi-frequency stimulation, combined with a new proposed coding method codifying up to 220 commands, which could be used to create a large multi-command brain computer interface. The advantages this method for commands codification and classification performance is analyzed in a five commands Brain computer interface. The classification of the electroencephalographic signals used in the interface was performed using several algorithms. The outcomes reveal that the best classification algorithm is a deep neural network, which gives a classification accuracy of 97.78 %. This algorithm, also, allows establishing the most relevant features of the electroencephalographic signal spectrums for the classification and information extraction from the evoked potentials.

AB - © 2018 IEEE. This work proposes a Brain Computer Interface based on using multi-frequency visual stimulation and deep neural networks for signals classification. The use of multi-frequency stimulation, combined with a new proposed coding method codifying up to 220 commands, which could be used to create a large multi-command brain computer interface. The advantages this method for commands codification and classification performance is analyzed in a five commands Brain computer interface. The classification of the electroencephalographic signals used in the interface was performed using several algorithms. The outcomes reveal that the best classification algorithm is a deep neural network, which gives a classification accuracy of 97.78 %. This algorithm, also, allows establishing the most relevant features of the electroencephalographic signal spectrums for the classification and information extraction from the evoked potentials.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85047345151&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85047345151&origin=inward

U2 - 10.1109/CONIELECOMP.2018.8327170

DO - 10.1109/CONIELECOMP.2018.8327170

M3 - Paper

SP - 18

EP - 24

ER -

Perez-Benitez JL, Perez-Benitez JA, Espina-Hernandez JH. Development of a brain computer interface interface using multi-frequency visual stimulation and deep neural networks. 2018. Paper presented at 2018 28th International Conference on Electronics, Communications and Computers, CONIELECOMP 2018, . https://doi.org/10.1109/CONIELECOMP.2018.8327170