FBATCNet: A Temporal Convolutional Network With Frequency Band Attention for Decoding Motor Imagery EEG
Motor imagery-based brain-computer interfaces (MI-BCIs) hold significant promise for upper limb rehabilitation in stroke patients. However, traditional MI paradigm primarily involves various limbs and fails to effectively address unilateral upper limb rehabilitation needs. In addition, compared to d...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10820511/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590357389377536 |
|---|---|
| author | Shuaishuai Ma Jidong Lv Wenjie Li Yan Liu Ling Zou Yakang Dai |
| author_facet | Shuaishuai Ma Jidong Lv Wenjie Li Yan Liu Ling Zou Yakang Dai |
| author_sort | Shuaishuai Ma |
| collection | DOAJ |
| description | Motor imagery-based brain-computer interfaces (MI-BCIs) hold significant promise for upper limb rehabilitation in stroke patients. However, traditional MI paradigm primarily involves various limbs and fails to effectively address unilateral upper limb rehabilitation needs. In addition, compared to decoding MI-EEG signals from different limbs, decoding MI-EEG signals from same limb faces more challenges. We introduced a novel tri-class fine motor imagery (FMI) paradigm and collected electroencephalogram (EEG) data from 20 healthy subjects for decoding research. Furthermore, we proposed a frequency band attention-based temporal convolutional network (FBATCNet) for MI-EEG decoding. First, an innovative use of the channel attention mechanism adaptively assigned weights to segmented EEG frequency bands, improving the frequency resolution of MI-EEG signals. Subsequently, convolutional block further integrated frequency-domain features and extracted spatial features. Finally, a temporal convolution block was utilized to capture advanced temporal features. The proposed model achieved accuracy of 84.73% on BCI Competition IV-2a (Dataset 1) and 66.06% on the private FMI dataset (Dataset 2). In the classification of subject dependent, the FBATCNet is better than the baseline methods mentioned in this paper. These results confirm that the FBATCNet is feasible and offer fresh insights for designing and applying FMI-BCI. |
| format | Article |
| id | doaj-art-c71f9792dbe04390942e7afad639a9f7 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-c71f9792dbe04390942e7afad639a9f72025-01-24T00:01:29ZengIEEEIEEE Access2169-35362025-01-0113112651127910.1109/ACCESS.2025.352552810820511FBATCNet: A Temporal Convolutional Network With Frequency Band Attention for Decoding Motor Imagery EEGShuaishuai Ma0https://orcid.org/0009-0003-0849-2580Jidong Lv1Wenjie Li2Yan Liu3https://orcid.org/0000-0001-9455-8133Ling Zou4https://orcid.org/0000-0001-5547-2871Yakang Dai5https://orcid.org/0000-0003-3357-1638School of Microelectronics and Control Engineering, Changzhou University, Changzhou, Jiangsu, ChinaSchool of Microelectronics and Control Engineering, Changzhou University, Changzhou, Jiangsu, ChinaSchool of Microelectronics and Control Engineering, Changzhou University, Changzhou, Jiangsu, ChinaDepartment of Medical Image, Chinese Academy of Science, Suzhou Institute of Biomedical Engineering and Technology, Suzhou, ChinaSchool of Microelectronics and Control Engineering, Changzhou University, Changzhou, Jiangsu, ChinaSchool of Microelectronics and Control Engineering, Changzhou University, Changzhou, Jiangsu, ChinaMotor imagery-based brain-computer interfaces (MI-BCIs) hold significant promise for upper limb rehabilitation in stroke patients. However, traditional MI paradigm primarily involves various limbs and fails to effectively address unilateral upper limb rehabilitation needs. In addition, compared to decoding MI-EEG signals from different limbs, decoding MI-EEG signals from same limb faces more challenges. We introduced a novel tri-class fine motor imagery (FMI) paradigm and collected electroencephalogram (EEG) data from 20 healthy subjects for decoding research. Furthermore, we proposed a frequency band attention-based temporal convolutional network (FBATCNet) for MI-EEG decoding. First, an innovative use of the channel attention mechanism adaptively assigned weights to segmented EEG frequency bands, improving the frequency resolution of MI-EEG signals. Subsequently, convolutional block further integrated frequency-domain features and extracted spatial features. Finally, a temporal convolution block was utilized to capture advanced temporal features. The proposed model achieved accuracy of 84.73% on BCI Competition IV-2a (Dataset 1) and 66.06% on the private FMI dataset (Dataset 2). In the classification of subject dependent, the FBATCNet is better than the baseline methods mentioned in this paper. These results confirm that the FBATCNet is feasible and offer fresh insights for designing and applying FMI-BCI.https://ieeexplore.ieee.org/document/10820511/Brain-computer interfacetemporal convolutional networkEEGfine motor imageryupper limb rehabilitation |
| spellingShingle | Shuaishuai Ma Jidong Lv Wenjie Li Yan Liu Ling Zou Yakang Dai FBATCNet: A Temporal Convolutional Network With Frequency Band Attention for Decoding Motor Imagery EEG IEEE Access Brain-computer interface temporal convolutional network EEG fine motor imagery upper limb rehabilitation |
| title | FBATCNet: A Temporal Convolutional Network With Frequency Band Attention for Decoding Motor Imagery EEG |
| title_full | FBATCNet: A Temporal Convolutional Network With Frequency Band Attention for Decoding Motor Imagery EEG |
| title_fullStr | FBATCNet: A Temporal Convolutional Network With Frequency Band Attention for Decoding Motor Imagery EEG |
| title_full_unstemmed | FBATCNet: A Temporal Convolutional Network With Frequency Band Attention for Decoding Motor Imagery EEG |
| title_short | FBATCNet: A Temporal Convolutional Network With Frequency Band Attention for Decoding Motor Imagery EEG |
| title_sort | fbatcnet a temporal convolutional network with frequency band attention for decoding motor imagery eeg |
| topic | Brain-computer interface temporal convolutional network EEG fine motor imagery upper limb rehabilitation |
| url | https://ieeexplore.ieee.org/document/10820511/ |
| work_keys_str_mv | AT shuaishuaima fbatcnetatemporalconvolutionalnetworkwithfrequencybandattentionfordecodingmotorimageryeeg AT jidonglv fbatcnetatemporalconvolutionalnetworkwithfrequencybandattentionfordecodingmotorimageryeeg AT wenjieli fbatcnetatemporalconvolutionalnetworkwithfrequencybandattentionfordecodingmotorimageryeeg AT yanliu fbatcnetatemporalconvolutionalnetworkwithfrequencybandattentionfordecodingmotorimageryeeg AT lingzou fbatcnetatemporalconvolutionalnetworkwithfrequencybandattentionfordecodingmotorimageryeeg AT yakangdai fbatcnetatemporalconvolutionalnetworkwithfrequencybandattentionfordecodingmotorimageryeeg |