EUVIMEDEUVIMED entdecken
Crossref

D-STNet: Dynamic Spectrum-Time Fusion With Adaptive Covariance Alignment for Motor Imagery EEG Decoding

Hailun Xu, Yifeng Sun, Zhiyong Zhou, Can Han, Jianwei Huang, Jun Wang

IEEE Sensors Journal · 2026-09 · 26 (18) · 27884-27894

DOI: 10.1109/jsen.2026.3715901 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, 2026-09. Verfasst von Hailun Xu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 44 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motor imagery electroencephalography (MI-EEG) decoding is limited by intersession nonstationarity and covariance mismatch. Existing alignment and deep decoding methods often use fixed preprocessing or unified feature learning, which limits adaptation to evolving covariance statistics and heterogeneous spectral–temporal patterns. We propose D-STNet, a dynamic spectrum-time fusion network that combines offline batch-level adaptive covariance alignment with dual-branch representation learning. Its static-dynamic Euclidean alignment (SD-EA) initializes a nontrainable covariance reference matrix from offline training data, updates it from unlabeled evaluation batches, and constructs a batch-specific whitening transform for covariance realignment while the trainable network parameters remain fixed. The backbone combines geometry-aware spectral learning (GASL) for covariance-aligned spectral–spatial representation, temporal gated multihead attention (TGMA) for waveform-level temporal dynamics, and dual-branch projection fusion (DBPF) for integration in a shared latent space. On brain–computer interface (BCI) Competition IV-2a, the High-Gamma Dataset, and BCI Competition IV-2b, D-STNet achieves accuracies of 83.00%, 94.36%, and 85.23%, outperforming the strongest baselines by 7.54, 1.63, and 1.47 percentage points, respectively. These results support offline covariance-statistics-level adaptive alignment as a compact strategy for MI-EEG decoding under covariance mismatch.

Zitieren

APA

Xu, H., Sun, Y., Zhou, Z., Han, C., Huang, J., & Wang, J. (2026). D-STNet: Dynamic Spectrum-Time Fusion With Adaptive Covariance Alignment for Motor Imagery EEG Decoding. IEEE Sensors Journal, 26(18), 27884-27894. https://doi.org/10.1109/jsen.2026.3715901

Vancouver

Xu H, Sun Y, Zhou Z, Han C, Huang J, Wang J. D-STNet: Dynamic Spectrum-Time Fusion With Adaptive Covariance Alignment for Motor Imagery EEG Decoding. IEEE Sensors Journal. 2026;26(18):27884-27894. doi:10.1109/jsen.2026.3715901

BibTeX
@article{Xu2026,
  author = {Xu, Hailun and Sun, Yifeng and Zhou, Zhiyong and Han, Can and Huang, Jianwei and Wang, Jun},
  title = {D-STNet: Dynamic Spectrum-Time Fusion With Adaptive Covariance Alignment for Motor Imagery EEG Decoding},
  journal = {IEEE Sensors Journal},
  year = {2026},
  volume = {26},
  number = {18},
  pages = {27884--27894},
  doi = {10.1109/jsen.2026.3715901}
}
Kostenlos starten →