Enhanced Online Continuous Brain-Control by Deep Learning-Based EEG Decoding
Objective: A growing amount of deep learning models for motor imagery (MI) decoding from electroencephalogram (EEG) have demonstrated their superiority over traditional machine learning approaches in offline dataset analysis. However, current online MI-based brain-computer interfaces (BCIs) still pr...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11087643/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849421034350968832 |
|---|---|
| author | Jiaheng Wang Lin Yao Yueming Wang |
| author_facet | Jiaheng Wang Lin Yao Yueming Wang |
| author_sort | Jiaheng Wang |
| collection | DOAJ |
| description | Objective: A growing amount of deep learning models for motor imagery (MI) decoding from electroencephalogram (EEG) have demonstrated their superiority over traditional machine learning approaches in offline dataset analysis. However, current online MI-based brain-computer interfaces (BCIs) still predominantly adopt machine learning decoders while falling short of high BCI performance. Yet, the generalization and advantages of deep learning-based EEG decoding in realistic BCI systems remain far unclear. Methods: We conduct a randomized and cross-session online MI-BCI study on 2D center-out tasks in 15 BCI-naive subjects. A newly proposed deep learning model named interactive frequency convolutional neural network (IFNet) is leveraged and rigorously compared with the prevailing benchmark namely filter-bank common spatial pattern (FBCSP) for online MI decoding. Results: Through extensive online analysis, the deep learning decoder consistently outperforms the classical counterpart across various performance metrics. In particular, IFNet significantly improves the average online task accuracy by 20% and 27% in two sessions compared with FBCSP, respectively. Moreover, a significant cross-session training effect is observed by the IFNet model (<inline-formula> <tex-math notation="LaTeX">${P}={0}.{017}$ </tex-math></inline-formula>) while not for the controlled method (<inline-formula> <tex-math notation="LaTeX">${P}={0}.{337}$ </tex-math></inline-formula>). Further offline evaluations also demonstrate the superior performance of IFNet over state-of-the-art deep learning models. Moreover, we present unique behavioral and neurophysiological insights underlying online brain-machine interaction. Conclusion: We present one of the first studies about online MI-BCIs using deep learning, achieving substantially enhanced online performance for continuous BCI control. Significance: This study suggests the good utility of deep learning in MI-BCIs and has implications for clinical applications such as stroke rehabilitation. |
| format | Article |
| id | doaj-art-b66abd7d5e714cda9ffeb63c96eb9f6c |
| institution | Kabale University |
| issn | 1534-4320 1558-0210 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj-art-b66abd7d5e714cda9ffeb63c96eb9f6c2025-08-20T03:31:34ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102025-01-01332834284610.1109/TNSRE.2025.359125411087643Enhanced Online Continuous Brain-Control by Deep Learning-Based EEG DecodingJiaheng Wang0https://orcid.org/0009-0005-0815-0518Lin Yao1https://orcid.org/0000-0003-2065-7280Yueming Wang2https://orcid.org/0000-0001-7742-0722Department of Neurobiology, Affiliated Mental Health Center and Hangzhou Seventh People’s Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaDepartment of Neurobiology, Affiliated Mental Health Center and Hangzhou Seventh People’s Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaNanhu Brain-Computer Interface Institute, Hangzhou, ChinaObjective: A growing amount of deep learning models for motor imagery (MI) decoding from electroencephalogram (EEG) have demonstrated their superiority over traditional machine learning approaches in offline dataset analysis. However, current online MI-based brain-computer interfaces (BCIs) still predominantly adopt machine learning decoders while falling short of high BCI performance. Yet, the generalization and advantages of deep learning-based EEG decoding in realistic BCI systems remain far unclear. Methods: We conduct a randomized and cross-session online MI-BCI study on 2D center-out tasks in 15 BCI-naive subjects. A newly proposed deep learning model named interactive frequency convolutional neural network (IFNet) is leveraged and rigorously compared with the prevailing benchmark namely filter-bank common spatial pattern (FBCSP) for online MI decoding. Results: Through extensive online analysis, the deep learning decoder consistently outperforms the classical counterpart across various performance metrics. In particular, IFNet significantly improves the average online task accuracy by 20% and 27% in two sessions compared with FBCSP, respectively. Moreover, a significant cross-session training effect is observed by the IFNet model (<inline-formula> <tex-math notation="LaTeX">${P}={0}.{017}$ </tex-math></inline-formula>) while not for the controlled method (<inline-formula> <tex-math notation="LaTeX">${P}={0}.{337}$ </tex-math></inline-formula>). Further offline evaluations also demonstrate the superior performance of IFNet over state-of-the-art deep learning models. Moreover, we present unique behavioral and neurophysiological insights underlying online brain-machine interaction. Conclusion: We present one of the first studies about online MI-BCIs using deep learning, achieving substantially enhanced online performance for continuous BCI control. Significance: This study suggests the good utility of deep learning in MI-BCIs and has implications for clinical applications such as stroke rehabilitation.https://ieeexplore.ieee.org/document/11087643/Brain-computer interfacemotor imagerydeep learningmachine learningonline continuous controlEEG |
| spellingShingle | Jiaheng Wang Lin Yao Yueming Wang Enhanced Online Continuous Brain-Control by Deep Learning-Based EEG Decoding IEEE Transactions on Neural Systems and Rehabilitation Engineering Brain-computer interface motor imagery deep learning machine learning online continuous control EEG |
| title | Enhanced Online Continuous Brain-Control by Deep Learning-Based EEG Decoding |
| title_full | Enhanced Online Continuous Brain-Control by Deep Learning-Based EEG Decoding |
| title_fullStr | Enhanced Online Continuous Brain-Control by Deep Learning-Based EEG Decoding |
| title_full_unstemmed | Enhanced Online Continuous Brain-Control by Deep Learning-Based EEG Decoding |
| title_short | Enhanced Online Continuous Brain-Control by Deep Learning-Based EEG Decoding |
| title_sort | enhanced online continuous brain control by deep learning based eeg decoding |
| topic | Brain-computer interface motor imagery deep learning machine learning online continuous control EEG |
| url | https://ieeexplore.ieee.org/document/11087643/ |
| work_keys_str_mv | AT jiahengwang enhancedonlinecontinuousbraincontrolbydeeplearningbasedeegdecoding AT linyao enhancedonlinecontinuousbraincontrolbydeeplearningbasedeegdecoding AT yuemingwang enhancedonlinecontinuousbraincontrolbydeeplearningbasedeegdecoding |