EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MGFNet: A Multi-Granularity Fusion Network with Coupling-Guided Sparse Routing for Hybrid EEG-fNIRS Decoding

Yan Zhang iD, Xiaoyu Gong iD, Xiaoyang Yuan iD

Sensors · 2026

DOI: 10.3390/s26113402 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Yan Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical Engineering and Automation, Harbin Institute of Technology, Harbin 150001, China. Hauptthemen laut MEDLINE: Electroencephalography, Neural Networks, Computer. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hybrid brain–computer interfaces (BCIs) have attracted growing research attention because they combine the millisecond-level temporal resolution of electroencephalography (EEG) with the spatially informative hemodynamic responses of functional near-infrared spectroscopy (fNIRS). However, most existing deep fusion methods rely on static late-fusion strategies, which tend to underexploit latent cross-modal dependencies and are vulnerable to modality-specific signal degradation. To address these limitations, we propose MGFNet, a multi-granularity fusion network for hybrid BCI decoding. MGFNet contains three components: (1) intra-modal encoders that learn modality-specific spatiotemporal representations from EEG, oxygenated hemoglobin (HbO), and deoxygenated hemoglobin (HbR) signals; (2) cross-modal interaction encoders that temporally align paired modalities and use dilated convolutions to capture long-range EEG-fNIRS dependencies; and (3) a Coupling-Guided Sparse Component Routing (CGSCR) module that estimates sample-specific cross-modal coupling and performs adaptive discrete routing. We further introduce a deep supervision strategy to stabilize optimization and improve branch-level discriminability. Under a within-subject held-out evaluation protocol on a public benchmark dataset, MGFNet achieved classification accuracies of 99.40% on the n-back task and 99.03% on the word generation (WG) task, outperforming representative comparison methods evaluated under a matched protocol. Ablation studies further confirmed the contributions of the intra-modal encoders, the cross-modal interaction encoders, and the CGSCR module. Under controlled EEG corruption with additive white Gaussian noise at −10 dB, MGFNet outperformed a static-fusion variant by 9.23 percentage points on the n-back task and 6.31 percentage points on the WG task. These results support the effectiveness of MGFNet in the present offline within-subject setting and indicate improved robustness under controlled single-modality degradation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyNeural Networks, ComputerHumansBrain-Computer InterfacesSpectroscopy, Near-InfraredAlgorithmsSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

CGSCREEG-fNIRS hybrid BCIadaptive routingcross-modal couplingmultimodal fusionrobustness

Autor:innen und Institutionen

  • School of Electrical Engineering and Automation, Harbin Institute of Technology, Harbin 150001, China.

ORCID-Profile: Yan Zhang, Xiaoyu Gong, Xiaoyang Yuan

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhang, Y., Gong, X., & Yuan, X. (2026). MGFNet: A Multi-Granularity Fusion Network with Coupling-Guided Sparse Routing for Hybrid EEG-fNIRS Decoding. Sensors. https://doi.org/10.3390/s26113402

Vancouver

Zhang Y, Gong X, Yuan X. MGFNet: A Multi-Granularity Fusion Network with Coupling-Guided Sparse Routing for Hybrid EEG-fNIRS Decoding. Sensors. 2026. doi:10.3390/s26113402

BibTeX
@article{Zhang2026,
  author = {Zhang, Yan and Gong, Xiaoyu and Yuan, Xiaoyang},
  title = {MGFNet: A Multi-Granularity Fusion Network with Coupling-Guided Sparse Routing for Hybrid EEG-fNIRS Decoding},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26113402}
}
Kostenlos starten →