A transfer learning framework based on motor imagery rehabilitation for stroke
Abstract Deep learning networks have been successfully applied to transfer functions so that the models can be adapted from the source domain to different target domains. This study uses multiple convolutional neural networks to decode the electroencephalogram (EEG) of stroke patients to design effe...
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/91657dde3ad84e49b736e205c3ce48b4 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:91657dde3ad84e49b736e205c3ce48b4 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:91657dde3ad84e49b736e205c3ce48b42021-12-02T17:13:22ZA transfer learning framework based on motor imagery rehabilitation for stroke10.1038/s41598-021-99114-12045-2322https://doaj.org/article/91657dde3ad84e49b736e205c3ce48b42021-10-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-99114-1https://doaj.org/toc/2045-2322Abstract Deep learning networks have been successfully applied to transfer functions so that the models can be adapted from the source domain to different target domains. This study uses multiple convolutional neural networks to decode the electroencephalogram (EEG) of stroke patients to design effective motor imagery (MI) brain-computer interface (BCI) system. This study has introduced ‘fine-tune’ to transfer model parameters and reduced training time. The performance of the proposed framework is evaluated by the abilities of the models for two-class MI recognition. The results show that the best framework is the combination of the EEGNet and ‘fine-tune’ transferred model. The average classification accuracy of the proposed model for 11 subjects is 66.36%, and the algorithm complexity is much lower than other models.These good performance indicate that the EEGNet model has great potential for MI stroke rehabilitation based on BCI system. It also successfully demonstrated the efficiency of transfer learning for improving the performance of EEG-based stroke rehabilitation for the BCI system.Fangzhou XuYunjing MiaoYanan SunDongju GuoJiali XuYuandong WangJincheng LiHan LiGege DongFenqi RongJiancai LengYang ZhangNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Fangzhou Xu Yunjing Miao Yanan Sun Dongju Guo Jiali Xu Yuandong Wang Jincheng Li Han Li Gege Dong Fenqi Rong Jiancai Leng Yang Zhang A transfer learning framework based on motor imagery rehabilitation for stroke |
| description |
Abstract Deep learning networks have been successfully applied to transfer functions so that the models can be adapted from the source domain to different target domains. This study uses multiple convolutional neural networks to decode the electroencephalogram (EEG) of stroke patients to design effective motor imagery (MI) brain-computer interface (BCI) system. This study has introduced ‘fine-tune’ to transfer model parameters and reduced training time. The performance of the proposed framework is evaluated by the abilities of the models for two-class MI recognition. The results show that the best framework is the combination of the EEGNet and ‘fine-tune’ transferred model. The average classification accuracy of the proposed model for 11 subjects is 66.36%, and the algorithm complexity is much lower than other models.These good performance indicate that the EEGNet model has great potential for MI stroke rehabilitation based on BCI system. It also successfully demonstrated the efficiency of transfer learning for improving the performance of EEG-based stroke rehabilitation for the BCI system. |
| format |
article |
| author |
Fangzhou Xu Yunjing Miao Yanan Sun Dongju Guo Jiali Xu Yuandong Wang Jincheng Li Han Li Gege Dong Fenqi Rong Jiancai Leng Yang Zhang |
| author_facet |
Fangzhou Xu Yunjing Miao Yanan Sun Dongju Guo Jiali Xu Yuandong Wang Jincheng Li Han Li Gege Dong Fenqi Rong Jiancai Leng Yang Zhang |
| author_sort |
Fangzhou Xu |
| title |
A transfer learning framework based on motor imagery rehabilitation for stroke |
| title_short |
A transfer learning framework based on motor imagery rehabilitation for stroke |
| title_full |
A transfer learning framework based on motor imagery rehabilitation for stroke |
| title_fullStr |
A transfer learning framework based on motor imagery rehabilitation for stroke |
| title_full_unstemmed |
A transfer learning framework based on motor imagery rehabilitation for stroke |
| title_sort |
transfer learning framework based on motor imagery rehabilitation for stroke |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/91657dde3ad84e49b736e205c3ce48b4 |
| work_keys_str_mv |
AT fangzhouxu atransferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT yunjingmiao atransferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT yanansun atransferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT dongjuguo atransferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT jialixu atransferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT yuandongwang atransferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT jinchengli atransferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT hanli atransferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT gegedong atransferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT fenqirong atransferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT jiancaileng atransferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT yangzhang atransferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT fangzhouxu transferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT yunjingmiao transferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT yanansun transferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT dongjuguo transferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT jialixu transferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT yuandongwang transferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT jinchengli transferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT hanli transferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT gegedong transferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT fenqirong transferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT jiancaileng transferlearningframeworkbasedonmotorimageryrehabilitationforstroke AT yangzhang transferlearningframeworkbasedonmotorimageryrehabilitationforstroke |
| _version_ |
1718381331353698304 |