EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A weighted multi-scale attention-enhanced temporal convolutional network for motor imagery EEG decoding in brain-computer interfaces

Zhongchen Song, Xuejun Zhang

Frontiers in Bioengineering and Biotechnology · 03.06.2026 · 14

DOI: 10.3389/fbioe.2026.1842610 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Bioengineering and Biotechnology, online erschienen am 03.06.2026. Verfasst von Zhongchen Song und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic and Optical Engineering & Flexible Electronics (Future Technology), Nanjing University of Posts and Telecommunications, Nanjing,…. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Nanjing University of Posts and Telecommunications.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate decoding of motor imagery electroencephalogram signals plays a critical role in brain-computer interfaces for neurorehabilitation and assistive technologies. However, existing multi-scale temporal methods often overlook scale-specific importance and fail to jointly capture transient and long-term neural dynamics, we propose a Weighted Multi-scale Attention-enhanced Temporal Convolutional Network (WMA-TCNet). The model employs parallel multi-scale temporal convolutions to capture neural patterns associated with distinct EEG rhythms. A global-aware scale attention mechanism adaptively weights each branch to emphasize task-relevant temporal information. A weighted Channel-Preserving Prior Path is introduced to maintain channel-wise dependencies and enhance spatial modeling stability across cortical regions. In addition, a temporal attention-guided TCN jointly captures local and long-range temporal dependencies. Experiments on BCI Competition IV 2a and 2b datasets show that WMA-TCNet achieves accuracies of 85.8% and 90.0% in subject-dependent settings, and 68.6% and 79.5% in cross-subject scenarios. These results demonstrate improved decoding performance and robustness, while providing a biologically meaningful framework for modeling multi-scale neural dynamics, with potential applications in brain-computer interfaces and neurorehabilitation.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismbrain-computer interfacechannel-preserving prior pathelectroencephalogrammotor imagerytemporal convolutional networkweighted feature fusion

Autor:innen und Institutionen

  • School of Electronic and Optical Engineering & Flexible Electronics (Future Technology), Nanjing University of Posts and Telecommunications, Nanjing, China.
  • Nation-Local Joint Project Engineering Lab of RF Integration & Micropackage, Nanjing University of Posts and Telecommunications, Nanjing, China.

Förderung

  • Nanjing University of Posts and Telecommunications

Zitieren

APA

Song, Z., & Zhang, X. (2026). A weighted multi-scale attention-enhanced temporal convolutional network for motor imagery EEG decoding in brain-computer interfaces. Frontiers in Bioengineering and Biotechnology, 14. https://doi.org/10.3389/fbioe.2026.1842610

Vancouver

Song Z, Zhang X. A weighted multi-scale attention-enhanced temporal convolutional network for motor imagery EEG decoding in brain-computer interfaces. Frontiers in Bioengineering and Biotechnology. 2026;14. doi:10.3389/fbioe.2026.1842610

BibTeX
@article{Song2026,
  author = {Song, Zhongchen and Zhang, Xuejun},
  title = {A weighted multi-scale attention-enhanced temporal convolutional network for motor imagery EEG decoding in brain-computer interfaces},
  journal = {Frontiers in Bioengineering and Biotechnology},
  year = {2026},
  volume = {14},
  doi = {10.3389/fbioe.2026.1842610}
}
Kostenlos starten →