EUVIMEDEUVIMED entdecken
Crossref

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

IEEE Transactions on Biomedical Engineering · 2023-02 · 70 (2) · 436-445

DOI: 10.1109/tbme.2022.3193277 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Biomedical Engineering, 2023-02. Verfasst von Ke Liu und 4 weiteren Autor:innen. Hauptthemen laut MEDLINE: Imagination, Brain-Computer Interfaces. Die Arbeit wurde bisher 150-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Chongqing, Technology Innovation 2030.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECT: Motor imagery (MI) is a mental process widely utilized as the experimental paradigm for brain-computer interfaces (BCIs) across a broad range of basic science and clinical studies. However, decoding intentions from MI remains challenging due to the inherent complexity of brain patterns relative to the small sample size available for machine learning. APPROACH: This paper proposes an end-to-end Filter-Bank Multiscale Convolutional Neural Network (FBMSNet) for MI classification. A filter bank is first employed to derive a multiview spectral representation of the EEG data. Mixed depthwise convolution is then applied to extract temporal features at multiple scales, followed by spatial filtering to mitigate volume conduction. Finally, with the joint supervision of cross-entropy and center loss, FBMSNet obtains features that maximize interclass dispersion and intraclass compactness. MAIN RESULTS: We compare FBMSNet with several state-of-the-art EEG decoding methods on two MI datasets: the BCI Competition IV 2a dataset and the OpenBMI dataset. FBMSNet significantly outperforms the benchmark methods by achieving 79.17% and 70.05% for four-class and two-class hold-out classification accuracy, respectively. SIGNIFICANCE: 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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ImaginationBrain-Computer InterfacesNeural Networks, ComputerMachine LearningBrainElectroencephalographyAlgorithms

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Chongqing
  • Technology Innovation 2030

Zitieren

APA

Liu, K., Yang, M., Yu, Z., Wang, G., & Wu, W. (2023). FBMSNet: A Filter-Bank Multi-Scale Convolutional Neural Network for EEG-Based Motor Imagery Decoding. IEEE Transactions on Biomedical Engineering, 70(2), 436-445. https://doi.org/10.1109/tbme.2022.3193277

Vancouver

Liu K, Yang M, Yu Z, Wang G, Wu W. FBMSNet: A Filter-Bank Multi-Scale Convolutional Neural Network for EEG-Based Motor Imagery Decoding. IEEE Transactions on Biomedical Engineering. 2023;70(2):436-445. doi:10.1109/tbme.2022.3193277

BibTeX
@article{Liu2023,
  author = {Liu, Ke and Yang, Mingzhao and Yu, Zhuliang and Wang, Guoyin and Wu, Wei},
  title = {FBMSNet: A Filter-Bank Multi-Scale Convolutional Neural Network for EEG-Based Motor Imagery Decoding},
  journal = {IEEE Transactions on Biomedical Engineering},
  year = {2023},
  volume = {70},
  number = {2},
  pages = {436--445},
  doi = {10.1109/tbme.2022.3193277}
}
Kostenlos starten →