/ EN
2026-07-21 00:00 China Papers Foundations & Methods Translated from EN

Adding EMG to Hybrid BCI Expands Command Space from 15 to 60 Targets

Summary Researchers have paired steady-state motion visual evoked potentials (SSMVEP) with electromyography (EMG) in a hybrid brain-computer interface, using a parallel architecture to expand the command space from 15 targets to 60. The multimodal setup reached an information transfer rate of 62.33 bits/min, against 42.49 bits/min for the best single-modality condition. Deep-learning decoding of the two signal streams held classification accuracy steady while lowering the effort required of users with severe motor impairment.
Why it matters Most efforts to widen a BCI's command set add EEG channels or lengthen stimulation windows; this one takes the extra dimension from residual muscle activity instead, shifting the design question from how many electrodes a system needs to which signals a given patient still has.

BCIwiki (bciwiki.com) — A hybrid brain-computer interface combining steady-state motion visual evoked potentials (SSMVEP) and electromyography (EMG) expanded the command space from 15 to 60 targets, achieving a multi-modal information transfer rate of 62.33 bits/min, outperforming the single-mode maximum of 42.49 bits/min. Researchers from Capital Medical University, Beijing Tian Tan Hospital, Nanchang University, the National Research Center for Rehabilitation Technical Aids, and the Chinese Institute for Brain Research reported the findings in the International Journal of Human–Computer Interaction on July 21, 2026.

The study used a parallel architecture that aligned a 15-target dynamic graphic zoom paradigm with four dental occlusion EMG patterns. Deep learning was employed for multimodal signal decoding, maintaining classification accuracy comparable to unimodal operations. The dual-channel processing contributed to the higher information transfer rate while reducing cognitive load. The authors said the interference-free mechanism breaks traditional bandwidth ceilings and validates an efficient 60-target control system for complex real-world deployment, potentially offering an accessible pathway for individuals with severe motor impairments.

Compiled by BCIwiki from public sources

Sources · 1
doi.org 2026-07-21

From these organizations

2026-09 Capital Medical University Anti-Fouling Coating Shields Neural Electrode, Signal Stays Clear for Six Months 2026-08 Capital Medical University BCI emerges as hotspot in post-stroke motor rehab 2026-08 Capital Medical University EEG-guided extraction switches speakers in 2.04 s
Read original ↗
Suggest a correction Revisions · none / EN
© 2026 BCIwiki.com Digest Topics Tips Subscribe Revisions About