Bidirectional feature pyramid attention-based temporal convolutional network model for motor imagery electroencephalogram classification
IntroductionAs an interactive method gaining popularity, brain-computer interfaces (BCIs) aim to facilitate communication between the brain and external devices. Among the various research topics in BCIs, the classification of motor imagery using electroencephalography (EEG) signals has the potentia...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2024-01-01
|
Series: | Frontiers in Neurorobotics |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnbot.2024.1343249/full |
_version_ | 1797339182461353984 |
---|---|
author | Xinghe Xie Xinghe Xie Liyan Chen Shujia Qin Fusheng Zha Xinggang Fan |
author_facet | Xinghe Xie Xinghe Xie Liyan Chen Shujia Qin Fusheng Zha Xinggang Fan |
author_sort | Xinghe Xie |
collection | DOAJ |
description | IntroductionAs an interactive method gaining popularity, brain-computer interfaces (BCIs) aim to facilitate communication between the brain and external devices. Among the various research topics in BCIs, the classification of motor imagery using electroencephalography (EEG) signals has the potential to greatly improve the quality of life for people with disabilities.MethodsThis technology assists them in controlling computers or other devices like prosthetic limbs, wheelchairs, and drones. However, the current performance of EEG signal decoding is not sufficient for real-world applications based on Motor Imagery EEG (MI-EEG). To address this issue, this study proposes an attention-based bidirectional feature pyramid temporal convolutional network model for the classification task of MI-EEG. The model incorporates a multi-head self-attention mechanism to weigh significant features in the MI-EEG signals. It also utilizes a temporal convolution network (TCN) to separate high-level temporal features. The signals are enhanced using the sliding-window technique, and channel and time-domain information of the MI-EEG signals is extracted through convolution.ResultsAdditionally, a bidirectional feature pyramid structure is employed to implement attention mechanisms across different scales and multiple frequency bands of the MI-EEG signals. The performance of our model is evaluated on the BCI Competition IV-2a dataset and the BCI Competition IV-2b dataset, and the results showed that our model outperformed the state-of-the-art baseline model, with an accuracy of 87.5 and 86.3% for the subject-dependent, respectively.DiscussionIn conclusion, the BFATCNet model offers a novel approach for EEG-based motor imagery classification in BCIs, effectively capturing relevant features through attention mechanisms and temporal convolutional networks. Its superior performance on the BCI Competition IV-2a and IV-2b datasets highlights its potential for real-world applications. However, its performance on other datasets may vary, necessitating further research on data augmentation techniques and integration with multiple modalities to enhance interpretability and generalization. Additionally, reducing computational complexity for real-time applications is an important area for future work. |
first_indexed | 2024-03-08T09:42:15Z |
format | Article |
id | doaj.art-ee102812889e4d8aa303659ad554f62e |
institution | Directory Open Access Journal |
issn | 1662-5218 |
language | English |
last_indexed | 2024-03-08T09:42:15Z |
publishDate | 2024-01-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Neurorobotics |
spelling | doaj.art-ee102812889e4d8aa303659ad554f62e2024-01-30T04:31:43ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182024-01-011810.3389/fnbot.2024.13432491343249Bidirectional feature pyramid attention-based temporal convolutional network model for motor imagery electroencephalogram classificationXinghe Xie0Xinghe Xie1Liyan Chen2Shujia Qin3Fusheng Zha4Xinggang Fan5Shenzhen Academy of Robotics, Shenzhen, Guangdong Province, ChinaFaculty of Applied Science, Macao Polytechnic University, Macau, Macao SAR, ChinaShenzhen Academy of Robotics, Shenzhen, Guangdong Province, ChinaShenzhen Academy of Robotics, Shenzhen, Guangdong Province, ChinaHarbin Institute of Technology, Harbin, Heilongjiang Province, ChinaInformation Engineering College, Zhijiang College of Zhejiang University of Technology, Shaoxing, ChinaIntroductionAs an interactive method gaining popularity, brain-computer interfaces (BCIs) aim to facilitate communication between the brain and external devices. Among the various research topics in BCIs, the classification of motor imagery using electroencephalography (EEG) signals has the potential to greatly improve the quality of life for people with disabilities.MethodsThis technology assists them in controlling computers or other devices like prosthetic limbs, wheelchairs, and drones. However, the current performance of EEG signal decoding is not sufficient for real-world applications based on Motor Imagery EEG (MI-EEG). To address this issue, this study proposes an attention-based bidirectional feature pyramid temporal convolutional network model for the classification task of MI-EEG. The model incorporates a multi-head self-attention mechanism to weigh significant features in the MI-EEG signals. It also utilizes a temporal convolution network (TCN) to separate high-level temporal features. The signals are enhanced using the sliding-window technique, and channel and time-domain information of the MI-EEG signals is extracted through convolution.ResultsAdditionally, a bidirectional feature pyramid structure is employed to implement attention mechanisms across different scales and multiple frequency bands of the MI-EEG signals. The performance of our model is evaluated on the BCI Competition IV-2a dataset and the BCI Competition IV-2b dataset, and the results showed that our model outperformed the state-of-the-art baseline model, with an accuracy of 87.5 and 86.3% for the subject-dependent, respectively.DiscussionIn conclusion, the BFATCNet model offers a novel approach for EEG-based motor imagery classification in BCIs, effectively capturing relevant features through attention mechanisms and temporal convolutional networks. Its superior performance on the BCI Competition IV-2a and IV-2b datasets highlights its potential for real-world applications. However, its performance on other datasets may vary, necessitating further research on data augmentation techniques and integration with multiple modalities to enhance interpretability and generalization. Additionally, reducing computational complexity for real-time applications is an important area for future work.https://www.frontiersin.org/articles/10.3389/fnbot.2024.1343249/fulldeep learningtemporal convolutional networksmultihead attentionelectroencephalogrammotion imagery |
spellingShingle | Xinghe Xie Xinghe Xie Liyan Chen Shujia Qin Fusheng Zha Xinggang Fan Bidirectional feature pyramid attention-based temporal convolutional network model for motor imagery electroencephalogram classification Frontiers in Neurorobotics deep learning temporal convolutional networks multihead attention electroencephalogram motion imagery |
title | Bidirectional feature pyramid attention-based temporal convolutional network model for motor imagery electroencephalogram classification |
title_full | Bidirectional feature pyramid attention-based temporal convolutional network model for motor imagery electroencephalogram classification |
title_fullStr | Bidirectional feature pyramid attention-based temporal convolutional network model for motor imagery electroencephalogram classification |
title_full_unstemmed | Bidirectional feature pyramid attention-based temporal convolutional network model for motor imagery electroencephalogram classification |
title_short | Bidirectional feature pyramid attention-based temporal convolutional network model for motor imagery electroencephalogram classification |
title_sort | bidirectional feature pyramid attention based temporal convolutional network model for motor imagery electroencephalogram classification |
topic | deep learning temporal convolutional networks multihead attention electroencephalogram motion imagery |
url | https://www.frontiersin.org/articles/10.3389/fnbot.2024.1343249/full |
work_keys_str_mv | AT xinghexie bidirectionalfeaturepyramidattentionbasedtemporalconvolutionalnetworkmodelformotorimageryelectroencephalogramclassification AT xinghexie bidirectionalfeaturepyramidattentionbasedtemporalconvolutionalnetworkmodelformotorimageryelectroencephalogramclassification AT liyanchen bidirectionalfeaturepyramidattentionbasedtemporalconvolutionalnetworkmodelformotorimageryelectroencephalogramclassification AT shujiaqin bidirectionalfeaturepyramidattentionbasedtemporalconvolutionalnetworkmodelformotorimageryelectroencephalogramclassification AT fushengzha bidirectionalfeaturepyramidattentionbasedtemporalconvolutionalnetworkmodelformotorimageryelectroencephalogramclassification AT xinggangfan bidirectionalfeaturepyramidattentionbasedtemporalconvolutionalnetworkmodelformotorimageryelectroencephalogramclassification |