AMEEGNet: attention-based multiscale EEGNet for effective motor imagery EEG decoding
Recently, electroencephalogram (EEG) based on motor imagery (MI) have gained significant traction in brain-computer interface (BCI) technology, particularly for the rehabilitation of paralyzed patients. But the low signal-to-noise ratio of MI EEG makes it difficult to decode effectively and hinders...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Neurorobotics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnbot.2025.1540033/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591662760591360 |
|---|---|
| author | Xuejian Wu Xuejian Wu Yaqi Chu Yaqi Chu Qing Li Yang Luo Yang Luo Yiwen Zhao Yiwen Zhao Xingang Zhao Xingang Zhao |
| author_facet | Xuejian Wu Xuejian Wu Yaqi Chu Yaqi Chu Qing Li Yang Luo Yang Luo Yiwen Zhao Yiwen Zhao Xingang Zhao Xingang Zhao |
| author_sort | Xuejian Wu |
| collection | DOAJ |
| description | Recently, electroencephalogram (EEG) based on motor imagery (MI) have gained significant traction in brain-computer interface (BCI) technology, particularly for the rehabilitation of paralyzed patients. But the low signal-to-noise ratio of MI EEG makes it difficult to decode effectively and hinders the development of BCI. In this paper, a method of attention-based multiscale EEGNet (AMEEGNet) was proposed to improve the decoding performance of MI-EEG. First, three parallel EEGNets with fusion transmission method were employed to extract the high-quality temporal-spatial feature of EEG data from multiple scales. Then, the efficient channel attention (ECA) module enhances the acquisition of more discriminative spatial features through a lightweight approach that weights critical channels. The experimental results demonstrated that the proposed model achieves decoding accuracies of 81.17, 89.83, and 95.49% on BCI-2a, 2b and HGD datasets. The results show that the proposed AMEEGNet effectively decodes temporal-spatial features, providing a novel perspective on MI-EEG decoding and advancing future BCI applications. |
| format | Article |
| id | doaj-art-d343e86eef194a9788ad40dc5231037f |
| institution | Kabale University |
| issn | 1662-5218 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurorobotics |
| spelling | doaj-art-d343e86eef194a9788ad40dc5231037f2025-01-22T07:15:54ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182025-01-011910.3389/fnbot.2025.15400331540033AMEEGNet: attention-based multiscale EEGNet for effective motor imagery EEG decodingXuejian Wu0Xuejian Wu1Yaqi Chu2Yaqi Chu3Qing Li4Yang Luo5Yang Luo6Yiwen Zhao7Yiwen Zhao8Xingang Zhao9Xingang Zhao10State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaSchool of Information Science and Engineering, Shenyang University of Chemical Technology, Shenyang, ChinaState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaRecently, electroencephalogram (EEG) based on motor imagery (MI) have gained significant traction in brain-computer interface (BCI) technology, particularly for the rehabilitation of paralyzed patients. But the low signal-to-noise ratio of MI EEG makes it difficult to decode effectively and hinders the development of BCI. In this paper, a method of attention-based multiscale EEGNet (AMEEGNet) was proposed to improve the decoding performance of MI-EEG. First, three parallel EEGNets with fusion transmission method were employed to extract the high-quality temporal-spatial feature of EEG data from multiple scales. Then, the efficient channel attention (ECA) module enhances the acquisition of more discriminative spatial features through a lightweight approach that weights critical channels. The experimental results demonstrated that the proposed model achieves decoding accuracies of 81.17, 89.83, and 95.49% on BCI-2a, 2b and HGD datasets. The results show that the proposed AMEEGNet effectively decodes temporal-spatial features, providing a novel perspective on MI-EEG decoding and advancing future BCI applications.https://www.frontiersin.org/articles/10.3389/fnbot.2025.1540033/fullmotor imagery (MI) EEGbrain-computer interfacesignal decodingmulti-scale decodingfusion transmissionefficient channel attention (ECA) mechanism |
| spellingShingle | Xuejian Wu Xuejian Wu Yaqi Chu Yaqi Chu Qing Li Yang Luo Yang Luo Yiwen Zhao Yiwen Zhao Xingang Zhao Xingang Zhao AMEEGNet: attention-based multiscale EEGNet for effective motor imagery EEG decoding Frontiers in Neurorobotics motor imagery (MI) EEG brain-computer interface signal decoding multi-scale decoding fusion transmission efficient channel attention (ECA) mechanism |
| title | AMEEGNet: attention-based multiscale EEGNet for effective motor imagery EEG decoding |
| title_full | AMEEGNet: attention-based multiscale EEGNet for effective motor imagery EEG decoding |
| title_fullStr | AMEEGNet: attention-based multiscale EEGNet for effective motor imagery EEG decoding |
| title_full_unstemmed | AMEEGNet: attention-based multiscale EEGNet for effective motor imagery EEG decoding |
| title_short | AMEEGNet: attention-based multiscale EEGNet for effective motor imagery EEG decoding |
| title_sort | ameegnet attention based multiscale eegnet for effective motor imagery eeg decoding |
| topic | motor imagery (MI) EEG brain-computer interface signal decoding multi-scale decoding fusion transmission efficient channel attention (ECA) mechanism |
| url | https://www.frontiersin.org/articles/10.3389/fnbot.2025.1540033/full |
| work_keys_str_mv | AT xuejianwu ameegnetattentionbasedmultiscaleeegnetforeffectivemotorimageryeegdecoding AT xuejianwu ameegnetattentionbasedmultiscaleeegnetforeffectivemotorimageryeegdecoding AT yaqichu ameegnetattentionbasedmultiscaleeegnetforeffectivemotorimageryeegdecoding AT yaqichu ameegnetattentionbasedmultiscaleeegnetforeffectivemotorimageryeegdecoding AT qingli ameegnetattentionbasedmultiscaleeegnetforeffectivemotorimageryeegdecoding AT yangluo ameegnetattentionbasedmultiscaleeegnetforeffectivemotorimageryeegdecoding AT yangluo ameegnetattentionbasedmultiscaleeegnetforeffectivemotorimageryeegdecoding AT yiwenzhao ameegnetattentionbasedmultiscaleeegnetforeffectivemotorimageryeegdecoding AT yiwenzhao ameegnetattentionbasedmultiscaleeegnetforeffectivemotorimageryeegdecoding AT xingangzhao ameegnetattentionbasedmultiscaleeegnetforeffectivemotorimageryeegdecoding AT xingangzhao ameegnetattentionbasedmultiscaleeegnetforeffectivemotorimageryeegdecoding |