A Study of Unilateral Upper Limb Fine Motor Imagery Decoding Using Frequency-Band Attention Network
Brain-computer interface (BCI) based motor imagery (MI) can assist stroke patients in upper limb rehabilitation and help restore motor function to a certain extent. However, the classical MI paradigm distinguishes different limbs and cannot effectively meet the needs of upper limb rehabilitation tra...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10453523/ |
| _version_ | 1797271527006142464 |
|---|---|
| author | Tianyu Shi Xiang Gu Hui Bi Jidong Lv Yan Liu Yakang Dai Ling Zou |
| author_facet | Tianyu Shi Xiang Gu Hui Bi Jidong Lv Yan Liu Yakang Dai Ling Zou |
| author_sort | Tianyu Shi |
| collection | DOAJ |
| description | Brain-computer interface (BCI) based motor imagery (MI) can assist stroke patients in upper limb rehabilitation and help restore motor function to a certain extent. However, the classical MI paradigm distinguishes different limbs and cannot effectively meet the needs of upper limb rehabilitation training for patients. Therefore, this paper designed a new paradigm for three motor imagery actions targeting different joints of the unilateral upper limb, and electroencephalogram (EEG) data from 20 healthy participants were collected for research analysis. A deep neural network model combining an attention mechanism for multiple frequency bands and a deep convolutional network were proposed to adaptively assign weight to the EEG data in different frequency bands. Then feature extraction was performed for each frequency band to learn further and to classify features. This model can obtain an average accuracy of 69.2% for the subject-independent case with the triple classification in the designed fine motor imagery (FMI) dataset, which is better than other controlled methods. Furthermore, ablation experiments were conducted for each module, demonstrating the effectiveness of each module. These results manifest the feasibility of our proposed method and the potential of FMI paradigm for BCI, providing a new training tool for upper limb rehabilitation after stroke. |
| first_indexed | 2024-03-07T14:04:52Z |
| format | Article |
| id | doaj.art-4f4301b0d8174ae4ae52f8bb40fd9fe1 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-07T14:04:52Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4f4301b0d8174ae4ae52f8bb40fd9fe12024-03-07T00:00:16ZengIEEEIEEE Access2169-35362024-01-0112326793269210.1109/ACCESS.2024.337190410453523A Study of Unilateral Upper Limb Fine Motor Imagery Decoding Using Frequency-Band Attention NetworkTianyu Shi0https://orcid.org/0009-0002-3596-8727Xiang Gu1Hui Bi2Jidong Lv3Yan Liu4https://orcid.org/0000-0001-9455-8133Yakang Dai5https://orcid.org/0000-0003-3357-1638Ling Zou6https://orcid.org/0000-0003-3357-1638School of Microelectronics and Control Engineering, Changzhou University, Changzhou, ChinaSchool of Computer Science and Artificial Intelligence, Changzhou University, Changzhou, ChinaSchool of Computer Science and Artificial Intelligence, Changzhou University, Changzhou, ChinaSchool of Microelectronics and Control Engineering, Changzhou University, Changzhou, ChinaDepartment of Medical Image, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, Suzhou, ChinaDepartment of Medical Image, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, Suzhou, ChinaSchool of Microelectronics and Control Engineering, Changzhou University, Changzhou, ChinaBrain-computer interface (BCI) based motor imagery (MI) can assist stroke patients in upper limb rehabilitation and help restore motor function to a certain extent. However, the classical MI paradigm distinguishes different limbs and cannot effectively meet the needs of upper limb rehabilitation training for patients. Therefore, this paper designed a new paradigm for three motor imagery actions targeting different joints of the unilateral upper limb, and electroencephalogram (EEG) data from 20 healthy participants were collected for research analysis. A deep neural network model combining an attention mechanism for multiple frequency bands and a deep convolutional network were proposed to adaptively assign weight to the EEG data in different frequency bands. Then feature extraction was performed for each frequency band to learn further and to classify features. This model can obtain an average accuracy of 69.2% for the subject-independent case with the triple classification in the designed fine motor imagery (FMI) dataset, which is better than other controlled methods. Furthermore, ablation experiments were conducted for each module, demonstrating the effectiveness of each module. These results manifest the feasibility of our proposed method and the potential of FMI paradigm for BCI, providing a new training tool for upper limb rehabilitation after stroke.https://ieeexplore.ieee.org/document/10453523/Brain–computer interfaceupper limb rehabilitationEEGfine motor imagerydeep learning |
| spellingShingle | Tianyu Shi Xiang Gu Hui Bi Jidong Lv Yan Liu Yakang Dai Ling Zou A Study of Unilateral Upper Limb Fine Motor Imagery Decoding Using Frequency-Band Attention Network IEEE Access Brain–computer interface upper limb rehabilitation EEG fine motor imagery deep learning |
| title | A Study of Unilateral Upper Limb Fine Motor Imagery Decoding Using Frequency-Band Attention Network |
| title_full | A Study of Unilateral Upper Limb Fine Motor Imagery Decoding Using Frequency-Band Attention Network |
| title_fullStr | A Study of Unilateral Upper Limb Fine Motor Imagery Decoding Using Frequency-Band Attention Network |
| title_full_unstemmed | A Study of Unilateral Upper Limb Fine Motor Imagery Decoding Using Frequency-Band Attention Network |
| title_short | A Study of Unilateral Upper Limb Fine Motor Imagery Decoding Using Frequency-Band Attention Network |
| title_sort | study of unilateral upper limb fine motor imagery decoding using frequency band attention network |
| topic | Brain–computer interface upper limb rehabilitation EEG fine motor imagery deep learning |
| url | https://ieeexplore.ieee.org/document/10453523/ |
| work_keys_str_mv | AT tianyushi astudyofunilateralupperlimbfinemotorimagerydecodingusingfrequencybandattentionnetwork AT xianggu astudyofunilateralupperlimbfinemotorimagerydecodingusingfrequencybandattentionnetwork AT huibi astudyofunilateralupperlimbfinemotorimagerydecodingusingfrequencybandattentionnetwork AT jidonglv astudyofunilateralupperlimbfinemotorimagerydecodingusingfrequencybandattentionnetwork AT yanliu astudyofunilateralupperlimbfinemotorimagerydecodingusingfrequencybandattentionnetwork AT yakangdai astudyofunilateralupperlimbfinemotorimagerydecodingusingfrequencybandattentionnetwork AT lingzou astudyofunilateralupperlimbfinemotorimagerydecodingusingfrequencybandattentionnetwork AT tianyushi studyofunilateralupperlimbfinemotorimagerydecodingusingfrequencybandattentionnetwork AT xianggu studyofunilateralupperlimbfinemotorimagerydecodingusingfrequencybandattentionnetwork AT huibi studyofunilateralupperlimbfinemotorimagerydecodingusingfrequencybandattentionnetwork AT jidonglv studyofunilateralupperlimbfinemotorimagerydecodingusingfrequencybandattentionnetwork AT yanliu studyofunilateralupperlimbfinemotorimagerydecodingusingfrequencybandattentionnetwork AT yakangdai studyofunilateralupperlimbfinemotorimagerydecodingusingfrequencybandattentionnetwork AT lingzou studyofunilateralupperlimbfinemotorimagerydecodingusingfrequencybandattentionnetwork |