A learnable EEG channel selection method for MI-BCI using efficient channel attention
IntroductionDuring electroencephalography (EEG)-based motor imagery-brain-computer interfaces (MI-BCIs) task, a large number of electrodes are commonly used, and consume much computational resources. Therefore, channel selection is crucial while ensuring classification accuracy.MethodsThis paper pro...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-10-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2023.1276067/full |
_version_ | 1797655212029116416 |
---|---|
author | Lina Tong Yihui Qian Liang Peng Chen Wang Zeng-Guang Hou Zeng-Guang Hou |
author_facet | Lina Tong Yihui Qian Liang Peng Chen Wang Zeng-Guang Hou Zeng-Guang Hou |
author_sort | Lina Tong |
collection | DOAJ |
description | IntroductionDuring electroencephalography (EEG)-based motor imagery-brain-computer interfaces (MI-BCIs) task, a large number of electrodes are commonly used, and consume much computational resources. Therefore, channel selection is crucial while ensuring classification accuracy.MethodsThis paper proposes a channel selection method by integrating the efficient channel attention (ECA) module with a convolutional neural network (CNN). During model training process, the ECA module automatically assigns the channel weights by evaluating the relative importance for BCI classification accuracy of every channel. Then a ranking of EEG channel importance can be established so as to select an appropriate number of channels to form a channel subset from the ranking. In this paper, the ECA module is embedded into a commonly used network for MI, and comparative experiments are conducted on the BCI Competition IV dataset 2a.Results and discussionThe proposed method achieved an average accuracy of 75.76% with all 22 channels and 69.52% with eight channels in a four-class classification task, outperforming other state-of-the-art EEG channel selection methods. The result demonstrates that the proposed method provides an effective channel selection approach for EEG-based MI-BCI. |
first_indexed | 2024-03-11T17:10:55Z |
format | Article |
id | doaj.art-f7164975258a480e94ff5ed64bd32cec |
institution | Directory Open Access Journal |
issn | 1662-453X |
language | English |
last_indexed | 2024-03-11T17:10:55Z |
publishDate | 2023-10-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Neuroscience |
spelling | doaj.art-f7164975258a480e94ff5ed64bd32cec2023-10-20T06:14:15ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2023-10-011710.3389/fnins.2023.12760671276067A learnable EEG channel selection method for MI-BCI using efficient channel attentionLina Tong0Yihui Qian1Liang Peng2Chen Wang3Zeng-Guang Hou4Zeng-Guang Hou5China University of Mining and Technology-Beijing, Beijing, ChinaChina University of Mining and Technology-Beijing, Beijing, ChinaState Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaChinese Academy of Sciences (CAS) Center for Excellence in Brain Science and Intelligence Technology, Beijing, ChinaIntroductionDuring electroencephalography (EEG)-based motor imagery-brain-computer interfaces (MI-BCIs) task, a large number of electrodes are commonly used, and consume much computational resources. Therefore, channel selection is crucial while ensuring classification accuracy.MethodsThis paper proposes a channel selection method by integrating the efficient channel attention (ECA) module with a convolutional neural network (CNN). During model training process, the ECA module automatically assigns the channel weights by evaluating the relative importance for BCI classification accuracy of every channel. Then a ranking of EEG channel importance can be established so as to select an appropriate number of channels to form a channel subset from the ranking. In this paper, the ECA module is embedded into a commonly used network for MI, and comparative experiments are conducted on the BCI Competition IV dataset 2a.Results and discussionThe proposed method achieved an average accuracy of 75.76% with all 22 channels and 69.52% with eight channels in a four-class classification task, outperforming other state-of-the-art EEG channel selection methods. The result demonstrates that the proposed method provides an effective channel selection approach for EEG-based MI-BCI.https://www.frontiersin.org/articles/10.3389/fnins.2023.1276067/fullbrain-computer interfacemotor imagerychannel selectiondeep learningattention mechanism |
spellingShingle | Lina Tong Yihui Qian Liang Peng Chen Wang Zeng-Guang Hou Zeng-Guang Hou A learnable EEG channel selection method for MI-BCI using efficient channel attention Frontiers in Neuroscience brain-computer interface motor imagery channel selection deep learning attention mechanism |
title | A learnable EEG channel selection method for MI-BCI using efficient channel attention |
title_full | A learnable EEG channel selection method for MI-BCI using efficient channel attention |
title_fullStr | A learnable EEG channel selection method for MI-BCI using efficient channel attention |
title_full_unstemmed | A learnable EEG channel selection method for MI-BCI using efficient channel attention |
title_short | A learnable EEG channel selection method for MI-BCI using efficient channel attention |
title_sort | learnable eeg channel selection method for mi bci using efficient channel attention |
topic | brain-computer interface motor imagery channel selection deep learning attention mechanism |
url | https://www.frontiersin.org/articles/10.3389/fnins.2023.1276067/full |
work_keys_str_mv | AT linatong alearnableeegchannelselectionmethodformibciusingefficientchannelattention AT yihuiqian alearnableeegchannelselectionmethodformibciusingefficientchannelattention AT liangpeng alearnableeegchannelselectionmethodformibciusingefficientchannelattention AT chenwang alearnableeegchannelselectionmethodformibciusingefficientchannelattention AT zengguanghou alearnableeegchannelselectionmethodformibciusingefficientchannelattention AT zengguanghou alearnableeegchannelselectionmethodformibciusingefficientchannelattention AT linatong learnableeegchannelselectionmethodformibciusingefficientchannelattention AT yihuiqian learnableeegchannelselectionmethodformibciusingefficientchannelattention AT liangpeng learnableeegchannelselectionmethodformibciusingefficientchannelattention AT chenwang learnableeegchannelselectionmethodformibciusingefficientchannelattention AT zengguanghou learnableeegchannelselectionmethodformibciusingefficientchannelattention AT zengguanghou learnableeegchannelselectionmethodformibciusingefficientchannelattention |