Cargando…

Classification of Motor Imagery Electroencephalography Signals Based on Image Processing Method

In recent years, more and more frameworks have been applied to brain-computer interface technology, and electroencephalogram-based motor imagery (MI-EEG) is developing rapidly. However, it is still a challenge to improve the accuracy of MI-EEG classification. A deep learning framework termed IS-CBAM...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Zhongye, Wang, Yijun, Song, Zhongyan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8309641/
https://www.ncbi.nlm.nih.gov/pubmed/34300386
http://dx.doi.org/10.3390/s21144646
_version_ 1783728569725222912
author Chen, Zhongye
Wang, Yijun
Song, Zhongyan
author_facet Chen, Zhongye
Wang, Yijun
Song, Zhongyan
author_sort Chen, Zhongye
collection PubMed
description In recent years, more and more frameworks have been applied to brain-computer interface technology, and electroencephalogram-based motor imagery (MI-EEG) is developing rapidly. However, it is still a challenge to improve the accuracy of MI-EEG classification. A deep learning framework termed IS-CBAM-convolutional neural network (CNN) is proposed to address the non-stationary nature, the temporal localization of excitation occurrence, and the frequency band distribution characteristics of the MI-EEG signal in this paper. First, according to the logically symmetrical relationship between the C3 and C4 channels, the result of the time-frequency image subtraction (IS) for the MI-EEG signal is used as the input of the classifier. It both reduces the redundancy and increases the feature differences of the input data. Second, the attention module is added to the classifier. A convolutional neural network is built as the base classifier, and information on the temporal location and frequency distribution of MI-EEG signal occurrences are adaptively extracted by introducing the Convolutional Block Attention Module (CBAM). This approach reduces irrelevant noise interference while increasing the robustness of the pattern. The performance of the framework was evaluated on BCI competition IV dataset 2b, where the mean accuracy reached 79.6%, and the average kappa value reached 0.592. The experimental results validate the feasibility of the framework and show the performance improvement of MI-EEG signal classification.
format Online
Article
Text
id pubmed-8309641
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83096412021-07-25 Classification of Motor Imagery Electroencephalography Signals Based on Image Processing Method Chen, Zhongye Wang, Yijun Song, Zhongyan Sensors (Basel) Article In recent years, more and more frameworks have been applied to brain-computer interface technology, and electroencephalogram-based motor imagery (MI-EEG) is developing rapidly. However, it is still a challenge to improve the accuracy of MI-EEG classification. A deep learning framework termed IS-CBAM-convolutional neural network (CNN) is proposed to address the non-stationary nature, the temporal localization of excitation occurrence, and the frequency band distribution characteristics of the MI-EEG signal in this paper. First, according to the logically symmetrical relationship between the C3 and C4 channels, the result of the time-frequency image subtraction (IS) for the MI-EEG signal is used as the input of the classifier. It both reduces the redundancy and increases the feature differences of the input data. Second, the attention module is added to the classifier. A convolutional neural network is built as the base classifier, and information on the temporal location and frequency distribution of MI-EEG signal occurrences are adaptively extracted by introducing the Convolutional Block Attention Module (CBAM). This approach reduces irrelevant noise interference while increasing the robustness of the pattern. The performance of the framework was evaluated on BCI competition IV dataset 2b, where the mean accuracy reached 79.6%, and the average kappa value reached 0.592. The experimental results validate the feasibility of the framework and show the performance improvement of MI-EEG signal classification. MDPI 2021-07-07 /pmc/articles/PMC8309641/ /pubmed/34300386 http://dx.doi.org/10.3390/s21144646 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Chen, Zhongye
Wang, Yijun
Song, Zhongyan
Classification of Motor Imagery Electroencephalography Signals Based on Image Processing Method
title Classification of Motor Imagery Electroencephalography Signals Based on Image Processing Method
title_full Classification of Motor Imagery Electroencephalography Signals Based on Image Processing Method
title_fullStr Classification of Motor Imagery Electroencephalography Signals Based on Image Processing Method
title_full_unstemmed Classification of Motor Imagery Electroencephalography Signals Based on Image Processing Method
title_short Classification of Motor Imagery Electroencephalography Signals Based on Image Processing Method
title_sort classification of motor imagery electroencephalography signals based on image processing method
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8309641/
https://www.ncbi.nlm.nih.gov/pubmed/34300386
http://dx.doi.org/10.3390/s21144646
work_keys_str_mv AT chenzhongye classificationofmotorimageryelectroencephalographysignalsbasedonimageprocessingmethod
AT wangyijun classificationofmotorimageryelectroencephalographysignalsbasedonimageprocessingmethod
AT songzhongyan classificationofmotorimageryelectroencephalographysignalsbasedonimageprocessingmethod