Cargando…

Vowel Imagery Decoding toward Silent Speech BCI Using Extreme Learning Machine with Electroencephalogram

The purpose of this study is to classify EEG data on imagined speech in a single trial. We recorded EEG data while five subjects imagined different vowels, /a/, /e/, /i/, /o/, and /u/. We divided each single trial dataset into thirty segments and extracted features (mean, variance, standard deviatio...

Descripción completa

Detalles Bibliográficos
Autores principales: Min, Beomjun, Kim, Jongin, Park, Hyeong-jun, Lee, Boreom
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi Publishing Corporation 2016
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5206788/
https://www.ncbi.nlm.nih.gov/pubmed/28097128
http://dx.doi.org/10.1155/2016/2618265
_version_ 1782490299612790784
author Min, Beomjun
Kim, Jongin
Park, Hyeong-jun
Lee, Boreom
author_facet Min, Beomjun
Kim, Jongin
Park, Hyeong-jun
Lee, Boreom
author_sort Min, Beomjun
collection PubMed
description The purpose of this study is to classify EEG data on imagined speech in a single trial. We recorded EEG data while five subjects imagined different vowels, /a/, /e/, /i/, /o/, and /u/. We divided each single trial dataset into thirty segments and extracted features (mean, variance, standard deviation, and skewness) from all segments. To reduce the dimension of the feature vector, we applied a feature selection algorithm based on the sparse regression model. These features were classified using a support vector machine with a radial basis function kernel, an extreme learning machine, and two variants of an extreme learning machine with different kernels. Because each single trial consisted of thirty segments, our algorithm decided the label of the single trial by selecting the most frequent output among the outputs of the thirty segments. As a result, we observed that the extreme learning machine and its variants achieved better classification rates than the support vector machine with a radial basis function kernel and linear discrimination analysis. Thus, our results suggested that EEG responses to imagined speech could be successfully classified in a single trial using an extreme learning machine with a radial basis function and linear kernel. This study with classification of imagined speech might contribute to the development of silent speech BCI systems.
format Online
Article
Text
id pubmed-5206788
institution National Center for Biotechnology Information
language English
publishDate 2016
publisher Hindawi Publishing Corporation
record_format MEDLINE/PubMed
spelling pubmed-52067882017-01-17 Vowel Imagery Decoding toward Silent Speech BCI Using Extreme Learning Machine with Electroencephalogram Min, Beomjun Kim, Jongin Park, Hyeong-jun Lee, Boreom Biomed Res Int Research Article The purpose of this study is to classify EEG data on imagined speech in a single trial. We recorded EEG data while five subjects imagined different vowels, /a/, /e/, /i/, /o/, and /u/. We divided each single trial dataset into thirty segments and extracted features (mean, variance, standard deviation, and skewness) from all segments. To reduce the dimension of the feature vector, we applied a feature selection algorithm based on the sparse regression model. These features were classified using a support vector machine with a radial basis function kernel, an extreme learning machine, and two variants of an extreme learning machine with different kernels. Because each single trial consisted of thirty segments, our algorithm decided the label of the single trial by selecting the most frequent output among the outputs of the thirty segments. As a result, we observed that the extreme learning machine and its variants achieved better classification rates than the support vector machine with a radial basis function kernel and linear discrimination analysis. Thus, our results suggested that EEG responses to imagined speech could be successfully classified in a single trial using an extreme learning machine with a radial basis function and linear kernel. This study with classification of imagined speech might contribute to the development of silent speech BCI systems. Hindawi Publishing Corporation 2016 2016-12-19 /pmc/articles/PMC5206788/ /pubmed/28097128 http://dx.doi.org/10.1155/2016/2618265 Text en Copyright © 2016 Beomjun Min et al. https://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Min, Beomjun
Kim, Jongin
Park, Hyeong-jun
Lee, Boreom
Vowel Imagery Decoding toward Silent Speech BCI Using Extreme Learning Machine with Electroencephalogram
title Vowel Imagery Decoding toward Silent Speech BCI Using Extreme Learning Machine with Electroencephalogram
title_full Vowel Imagery Decoding toward Silent Speech BCI Using Extreme Learning Machine with Electroencephalogram
title_fullStr Vowel Imagery Decoding toward Silent Speech BCI Using Extreme Learning Machine with Electroencephalogram
title_full_unstemmed Vowel Imagery Decoding toward Silent Speech BCI Using Extreme Learning Machine with Electroencephalogram
title_short Vowel Imagery Decoding toward Silent Speech BCI Using Extreme Learning Machine with Electroencephalogram
title_sort vowel imagery decoding toward silent speech bci using extreme learning machine with electroencephalogram
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5206788/
https://www.ncbi.nlm.nih.gov/pubmed/28097128
http://dx.doi.org/10.1155/2016/2618265
work_keys_str_mv AT minbeomjun vowelimagerydecodingtowardsilentspeechbciusingextremelearningmachinewithelectroencephalogram
AT kimjongin vowelimagerydecodingtowardsilentspeechbciusingextremelearningmachinewithelectroencephalogram
AT parkhyeongjun vowelimagerydecodingtowardsilentspeechbciusingextremelearningmachinewithelectroencephalogram
AT leeboreom vowelimagerydecodingtowardsilentspeechbciusingextremelearningmachinewithelectroencephalogram