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...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiaheng Wang, Lin Yao, Yueming Wang
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&#x2019;s Hospital, Zhejiang University School of Medicine, Hangzhou, ChinaDepartment of Neurobiology, Affiliated Mental Health Center and Hangzhou Seventh People&#x2019;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