2026-09-07 00:00 China Papers Foundations & Methods Translated from EN

Peking Union Medical College Team's 480-Target Hybrid BCI Hits 260 Bits per Minute

Summary A team at the Institute of Biomedical Engineering, Chinese Academy of Medical Sciences and Peking Union Medical College, has built a hybrid brain-computer interface (BCI) that combines surface electromyography (sEMG) with steady-state visual evoked potentials (SSVEP), encoding 480 targets with 120 flicker frequencies and four hand gestures. In online experiments it achieved a mean classification accuracy of 84.55 ± 7.23% and a mean information transfer rate (ITR), a key measure of practical BCI performance, of 260.07 ± 30.41 bits/min. Its command set matches the largest target counts in existing systems, and the authors place its performance among the top, offering a technical reference for large-command-set BCIs. The work appeared in Cognitive Neurodynamics on September 7, 2026.

Why it matters Matching the largest command sets reported so far while keeping ITR high, the study shows that pairing muscle signals with visual evoked potentials is a workable way to scale BCI commands, though accuracy still has headroom and results come from controlled online sessions rather than real-world use.

BCIwiki (bciwiki.com) — A hybrid brain-computer interface (BCI) combining surface electromyography (sEMG) and steady-state visual evoked potentials (SSVEP) encoded 480 targets using 120 flicker frequencies and 4 gesture movements, achieving an average classification accuracy of 84.55 ± 7.23% and an information transfer rate (ITR) of 260.07 ± 30.41 bits/min in online experiments. The work, by researchers at the Institute of Biomedical Engineering, Tianjin Institutes of Health Science, Chinese Academy of Medical Sciences and Peking Union Medical College, appeared in Cognitive Neurodynamics on September 7, 2026.The system uses high-density electrodes to acquire EEG signals, aiming to broaden the command set and improve ITR. The authors said the system’s command-set size is nearly identical to that of the state-of-the-art BCI with the maximum number of targets, and its performance ranks among the top tier, providing a technical reference for implementing BCIs with large command sets.

Compiled by BCIwiki from public sources

Sources · 1

pubmed.ncbi.nlm.nih.gov 2026-09-07

Chinese Academy of Medical Sciences & Peking Union Medical College Decoding Algorithms EEG Non-invasive BCI China

Chinese Academy of Medical Sciences & Peking Union Medical College timeline

2026-08 MRieHy Framework for Online MI-BCI Adaptation 2026-07 Miniscope Enables Real-Time Neural Decoding 2026-04 Feasibility of a Hybrid SSVEP-Motor Imagery BCI with Robotic Feedback for Stroke Upper Limb Rehabilitation All entries →

Read original ↗

Suggest a correction Revisions · none 中 / EN