Jiayuan He

Biophysically constrained learning from healthy neural priors improves motor decoding in pathological cortical networks

High-performance brain-computer interfaces (BCIs) rely on stable neural representations, yet brain functional impairments inherently disrupt canonical encoding, creating a fundamental decoding paradox. Conventional data-driven approaches struggle to bridge this gap because of pathological data scarcity and heterogeneit...

Bidirectional Reasoning for Channel Selection of Electroencephalography in Auditory Attention Decoding

Auditory attention decoding (AAD) from electroencephalography (EEG) is a promising neural sensing approach for neuro-steered hearing devices, but dense electrode configurations limit portability and wearability, making reduced-channel EEG measurement essential for wearable biomedical instrumentation. Current channel-se...

Toward Intraoperative Glioma Localization: Exploring the Relationship Between Tumor Invasion Depth and Electrocorticography Signals.

This study suggests that tumor infiltration is associated with suppression of cortical electrical activity and provides preliminary evidence of a relationship between ECoG signals and glioma invasion depth and indicates a potential exploratory framework for assessing tumor infiltration intraoperatively.

Identifying brain-computer interface translational priorities with an outlook on the field in 2035

Brain–computer interfaces (BCIs) have advanced rapidly, particularly over the past few decades, evolving from experimental demonstrations to powerful research tools and early-stage clinical technologies. Invasive, semi-invasive, and non-invasive modalities now enable neural decoding, neuromodulation, and functional res...

Vision-based postural kinematics reveal brain–body workload coupling in ship-motion digital control operation