FBMSNet: A Filter-Bank Multi-Scale Convolutional Neural Network for EEG-Based Motor Imagery Decoding

Ke Liu; Mingzhao Yang; Zhuliang Yu; Guoyin Wang; Wei Wu

doi:10.1109/tbme.2022.3193277

July 22, 2022IEEE Transactions on Biomedical Engineering

FBMSNet: A Filter-Bank Multi-Scale Convolutional Neural Network for EEG-Based Motor Imagery Decoding

View at Publisher

Ask AI

Bookmark

Share

Key Points

To introduce and evaluate FBMSNet, a filter-bank multi-scale convolutional neural network architecture tailored for decoding electroencephalography signals during motor imagery tasks.
Designed a neural network architecture combining multi-frequency filter-bank representations with multi-scale temporal and spatial convolutional layers.
Evaluated model decoding performance on motor imagery electroencephalography datasets for brain-computer interface applications and released open-source code.
FBMSNet improves electroencephalography signal decoding performance relative to baseline brain-computer interface pipelines.
The multi-scale filter-bank feature representation enhances robustness across motor imagery classification tasks.

Ask about this paper

Answers are grounded in this paper and cite their sources.

Implication

Machine learning study demonstrates enhanced EEG decoding accuracy during motor imagery tasks, suggesting greater robustness for brain-computer interface applications.

Abstract

These results demonstrate the efficacy of FBMSNet in improving EEG decoding performance toward more robust BCI applications. The FBMSNet source code is available at https://github.com/Want2Vanish/FBMSNet.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Liu et al. (2022) studied this question.

synapsesocial.com/papers/69e1fe4f45c770d357ad3eba https://doi.org/10.1109/tbme.2022.3193277

View at Publisher

Ask AI

Bookmark

Share

FBMSNet: A Filter-Bank Multi-Scale Convolutional Neural Network for EEG-Based Motor Imagery Decoding

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

FBMSNet: A Filter-Bank Multi-Scale Convolutional Neural Network for EEG-Based Motor Imagery Decoding

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading