NVC-DSDNet: neurovascular coupling-aware delay alignment and subspace disentanglement network for hybrid EEG–fNIRS brain–computer interfaces

Hybrid EEG–fNIRS brain–computer interfaces combine rapid electrophysiological activity with hemodynamic information, but neurovascular latency and entangled multimodal features hinder effective fusion. We propose the Neurovascular Coupling-Aware Delay Alignment and Subspace Disentanglement Network (NVC-DSDNet), which couples delay-aware attention with shared–private neural subspaces. EEG responses serve as temporal anchors that retrieve task-relevant fNIRS features over candidate delays, while Neural Feature Subspace Decomposition separates shared neural intent from modality-specific information. An adaptive multi-head decision module then weights unimodal and fused predictions at the sample level. In subject-independent five-fold cross-validation, NVC-DSDNet achieved accuracies of 72.67% for motor imagery, 82.79% for mental arithmetic, and 76.17% for word generation. Learned delay weights peaked at 4.5–5.5 s for motor imagery and shifted to 6.0–9.0 s for mental arithmetic, consistent with task-dependent hemodynamic time courses. These results show that coupling-aware temporal alignment and subspace disentanglement can improve multimodal neural decoding while retaining neurophysiological interpretability.