Cargando…
Local and global convolutional transformer-based motor imagery EEG classification
Transformer, a deep learning model with the self-attention mechanism, combined with the convolution neural network (CNN) has been successfully applied for decoding electroencephalogram (EEG) signals in Motor Imagery (MI) Brain-Computer Interface (BCI). However, the extremely non-linear, nonstationar...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10469791/ https://www.ncbi.nlm.nih.gov/pubmed/37662099 http://dx.doi.org/10.3389/fnins.2023.1219988 |
_version_ | 1785099523750625280 |
---|---|
author | Zhang, Jiayang Li, Kang Yang, Banghua Han, Xiaofei |
author_facet | Zhang, Jiayang Li, Kang Yang, Banghua Han, Xiaofei |
author_sort | Zhang, Jiayang |
collection | PubMed |
description | Transformer, a deep learning model with the self-attention mechanism, combined with the convolution neural network (CNN) has been successfully applied for decoding electroencephalogram (EEG) signals in Motor Imagery (MI) Brain-Computer Interface (BCI). However, the extremely non-linear, nonstationary characteristics of the EEG signals limits the effectiveness and efficiency of the deep learning methods. In addition, the variety of subjects and the experimental sessions impact the model adaptability. In this study, we propose a local and global convolutional transformer-based approach for MI-EEG classification. The local transformer encoder is combined to dynamically extract temporal features and make up for the shortcomings of the CNN model. The spatial features from all channels and the difference in hemispheres are obtained to improve the robustness of the model. To acquire adequate temporal-spatial feature representations, we combine the global transformer encoder and Densely Connected Network to improve the information flow and reuse. To validate the performance of the proposed model, three scenarios including within-session, cross-session and two-session are designed. In the experiments, the proposed method achieves up to 1.46%, 7.49% and 7.46% accuracy improvement respectively in the three scenarios for the public Korean dataset compared with current state-of-the-art models. For the BCI competition IV 2a dataset, the proposed model also achieves a 2.12% and 2.21% improvement for the cross-session and two-session scenarios respectively. The results confirm that the proposed approach can effectively extract much richer set of MI features from the EEG signals and improve the performance in the BCI applications. |
format | Online Article Text |
id | pubmed-10469791 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-104697912023-09-01 Local and global convolutional transformer-based motor imagery EEG classification Zhang, Jiayang Li, Kang Yang, Banghua Han, Xiaofei Front Neurosci Neuroscience Transformer, a deep learning model with the self-attention mechanism, combined with the convolution neural network (CNN) has been successfully applied for decoding electroencephalogram (EEG) signals in Motor Imagery (MI) Brain-Computer Interface (BCI). However, the extremely non-linear, nonstationary characteristics of the EEG signals limits the effectiveness and efficiency of the deep learning methods. In addition, the variety of subjects and the experimental sessions impact the model adaptability. In this study, we propose a local and global convolutional transformer-based approach for MI-EEG classification. The local transformer encoder is combined to dynamically extract temporal features and make up for the shortcomings of the CNN model. The spatial features from all channels and the difference in hemispheres are obtained to improve the robustness of the model. To acquire adequate temporal-spatial feature representations, we combine the global transformer encoder and Densely Connected Network to improve the information flow and reuse. To validate the performance of the proposed model, three scenarios including within-session, cross-session and two-session are designed. In the experiments, the proposed method achieves up to 1.46%, 7.49% and 7.46% accuracy improvement respectively in the three scenarios for the public Korean dataset compared with current state-of-the-art models. For the BCI competition IV 2a dataset, the proposed model also achieves a 2.12% and 2.21% improvement for the cross-session and two-session scenarios respectively. The results confirm that the proposed approach can effectively extract much richer set of MI features from the EEG signals and improve the performance in the BCI applications. Frontiers Media S.A. 2023-08-17 /pmc/articles/PMC10469791/ /pubmed/37662099 http://dx.doi.org/10.3389/fnins.2023.1219988 Text en Copyright © 2023 Zhang, Li, Yang and Han. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Neuroscience Zhang, Jiayang Li, Kang Yang, Banghua Han, Xiaofei Local and global convolutional transformer-based motor imagery EEG classification |
title | Local and global convolutional transformer-based motor imagery EEG classification |
title_full | Local and global convolutional transformer-based motor imagery EEG classification |
title_fullStr | Local and global convolutional transformer-based motor imagery EEG classification |
title_full_unstemmed | Local and global convolutional transformer-based motor imagery EEG classification |
title_short | Local and global convolutional transformer-based motor imagery EEG classification |
title_sort | local and global convolutional transformer-based motor imagery eeg classification |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10469791/ https://www.ncbi.nlm.nih.gov/pubmed/37662099 http://dx.doi.org/10.3389/fnins.2023.1219988 |
work_keys_str_mv | AT zhangjiayang localandglobalconvolutionaltransformerbasedmotorimageryeegclassification AT likang localandglobalconvolutionaltransformerbasedmotorimageryeegclassification AT yangbanghua localandglobalconvolutionaltransformerbasedmotorimageryeegclassification AT hanxiaofei localandglobalconvolutionaltransformerbasedmotorimageryeegclassification |