EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

NeuroMambaNet: A Prior-Integrated Dual-Stream Mamba Network for Robust Cross-Subject Motor Imagery EEG Classification

Weisi Chen, Yuan Li, Lin Yuanbo Wu, Xu Zhang

Big Data and Cognitive Computing · 11.11.2026 · 10 (11) · 385

DOI: 10.3390/bdcc10110385 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 11.11.2026. Verfasst von Weisi Chen und 3 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Major Science and Technology Project under the Xiamen Major Innovation Platform Program, General Project of the Social Science Foundation of Fujian Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cross-subject motor-imagery electroencephalography (MI-EEG) classification remains challenging due to substantial inter-subject variability and non-stationarity, which cause task-relevant spectral and spatial patterns to vary across users and reduce the robustness of models trained on source subjects. To address this issue, we propose NeuroMambaNet, a brain-informed dual-stream network that explicitly integrates spectral, spatial, and rhythmic priors. In the frequency-enhanced stream, a Mamba-Augmented Multi-Band Oscillation (MAMBO) module decomposes EEG with a Discrete Wavelet Transform (DWT), models the physiologically relevant θ, α, β, and γ sub-bands using independent Mamba blocks, and reconstructs a band-enhanced signal through inverse DWT (IDWT). In parallel, the raw stream extracts complementary spatial representations using two Brain-Region Prior Grouping (BRDW) branches based on left–central–right and central–outer electrode partitions. β-band evidence from frontal-central electrodes is then used by a lightweight Beta-Gate module to adaptively weight the two spatial branches. The frequency-enhanced and gated raw representations are fused at a later stage and processed by a global temporal convolution for classification. Under a strict leave-one-subject-out (LOSO) protocol, NeuroMambaNet achieves an average accuracy of 59.04% and a Cohen’s κ of 0.4539 on the BCI IV-2a dataset, and 69.20% and 0.3839, respectively, on the CBCIC dataset, outperforming evaluated baseline methods and demonstrating the potential of the proposed architecture for subject-independent MI-EEG classification.

Förderung

  • Major Science and Technology Project under the Xiamen Major Innovation Platform Program
  • General Project of the Social Science Foundation of Fujian Province

Zitieren

APA

Chen, W., Li, Y., Wu, L. Y., & Zhang, X. (2026). NeuroMambaNet: A Prior-Integrated Dual-Stream Mamba Network for Robust Cross-Subject Motor Imagery EEG Classification. Big Data and Cognitive Computing, 10(11), 385. https://doi.org/10.3390/bdcc10110385

Vancouver

Chen W, Li Y, Wu LY, Zhang X. NeuroMambaNet: A Prior-Integrated Dual-Stream Mamba Network for Robust Cross-Subject Motor Imagery EEG Classification. Big Data and Cognitive Computing. 2026;10(11):385. doi:10.3390/bdcc10110385

BibTeX
@article{Chen2026,
  author = {Chen, Weisi and Li, Yuan and Wu, Lin Yuanbo and Zhang, Xu},
  title = {NeuroMambaNet: A Prior-Integrated Dual-Stream Mamba Network for Robust Cross-Subject Motor Imagery EEG Classification},
  journal = {Big Data and Cognitive Computing},
  year = {2026},
  volume = {10},
  number = {11},
  pages = {385},
  doi = {10.3390/bdcc10110385}
}
Kostenlos starten →