2026-08-06 00:00 China Canada Papers Foundations & Methods Translated from EN

BiGSTF-Net: Inter-Modal Mutual Guidance and Intra-Modal Spatio-Temporal Fusion for EEG-fNIRS Cognitive Classification

Summary The study proposes BiGSTF-Net, a multimodal architecture that exploits the complementary properties of EEG and functional near-infrared spectroscopy (fNIRS) for cognitive-state decoding: heterogeneous spatio-temporal extractors capture each modality's representations, a modal residual interaction unit provides bidirectional cross-modal guidance, and a spatio-temporal gating unit fuses intra-modal features. Under cross-session evaluation on multiple BCI datasets, BiGSTF-Net consistently outperformed representative multimodal fusion baselines; ablations validated each component and visualizations matched the known neurophysiological features of the two signals.

Why it matters Its bidirectional cross-modal guidance goes beyond concatenating EEG and fNIRS, showing how to fuse temporal and hemodynamic signals in a way that survives cross-session shifts.

This study, published in Journal of Neural Engineering, proposes BiGSTF-Net, a multimodal architecture that improves cognitive state decoding by leveraging the complementary properties of EEG and functional near-infrared spectroscopy (fNIRS), using a modal residual interaction unit for bidirectional inter-modal guidance and a spatio-temporal gated unit for intra-modal feature integration.

Under cross-session evaluation on multiple BCI datasets, BiGSTF-Net consistently outperformed representative multimodal fusion baselines; ablation studies verified the effectiveness of its architectural components, and visualization analyses revealed activation patterns consistent with known neurophysiological characteristics of EEG and fNIRS signals. PMID 42556397, DOI 10.1088/1741-2552/ae9595

Compiled by BCIwiki from public sources

Sources · 1

pubmed.ncbi.nlm.nih.gov 2026-08-06

Simon Fraser University Beijing Jiaotong University Decoding Algorithms China Canada

Read original ↗

Suggest a correction Revisions · none 中 / EN