EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Decoupled Bidirectional Spatio-Temporal Fusion Network for Hybrid EEG-fNIRS Cognitive Task Classification

Zirui Wang, Guanghao Huang iD, Zhuochao Chen, Xiaorui Liu, Yinhua Liu, Keum-Shik Hong iD

Brain Sciences · 21.02.2026 · 16 (2) · 241

DOI: 10.3390/brainsci16020241 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Brain Sciences, online erschienen am 21.02.2026. Verfasst von Zirui Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Future, School of Automation, Qingdao University, Qingdao 266071, China. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Multimodal neuroimaging, particularly the integration of electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS), has emerged as a key methodology for investigating brain function and classifying neural activity. However, the efficient fusion of these two signals remains a formidable challenge due to their significant spatio-temporal heterogeneity. This paper presents the BiSTF-Net, which integrates decoupled and bi-directional spatio-temporal fusion mechanisms to enhance the performance of cognitive task recognition.

Methods

In BiSTF-Net, the spatial features of EEG and fNIRS are mutually guided and enhanced through an efficient bi-directional cross modal guidance (Bi-CMG). Then, the temporal latencies of fNIRS signals are aligned in a data-driven manner using adaptive temporal alignment (ATA). Subsequently, the aligned features are deeply fused into a modality-invariant, discriminative representation via a symmetric cross-attention fusion (SCAF) module.

Results

Evaluated on the mental arithmetic (MA), motor imagery (MI), and word generation (WG) tasks, the BiSTF-Net achieves average accuracies of 83.33%, 82.09%, and 84.99% respectively.

Conclusions

The BiSTF-Net exhibits superior performance compared to the existing methods, offers a robust and interpretable solution for multimodal EEG-fNIRS cognitive task classification, and provides a methodological foundation for future extensions to other multimodal data and broader real-world clinical applications.

Schlagwörter

Stichwörter der Autor:innen

EEGcognitive task classificationdecoupled fusionfNIRSmultimodal neuroimagingspatio-temporal alignment

Autor:innen und Institutionen

  • Institute for Future, School of Automation, Qingdao University, Qingdao 266071, China.
  • School of Mechanical Engineering, Pusan National University, Busan 46241, Republic of Korea.

ORCID-Profile: Guanghao Huang, Keum-Shik Hong

Zitieren

APA

Wang, Z., Huang, G., Chen, Z., Liu, X., Liu, Y., & Hong, K. S. (2026). Decoupled Bidirectional Spatio-Temporal Fusion Network for Hybrid EEG-fNIRS Cognitive Task Classification. Brain Sciences, 16(2), 241. https://doi.org/10.3390/brainsci16020241

Vancouver

Wang Z, Huang G, Chen Z, Liu X, Liu Y, Hong KS. Decoupled Bidirectional Spatio-Temporal Fusion Network for Hybrid EEG-fNIRS Cognitive Task Classification. Brain Sciences. 2026;16(2):241. doi:10.3390/brainsci16020241

BibTeX
@article{Wang2026,
  author = {Wang, Zirui and Huang, Guanghao and Chen, Zhuochao and Liu, Xiaorui and Liu, Yinhua and Hong, Keum-Shik},
  title = {Decoupled Bidirectional Spatio-Temporal Fusion Network for Hybrid EEG-fNIRS Cognitive Task Classification},
  journal = {Brain Sciences},
  year = {2026},
  volume = {16},
  number = {2},
  pages = {241},
  doi = {10.3390/brainsci16020241}
}
Kostenlos starten →