BCIwiki — Brain-computer interface news, research and industry database

On May 8, 2026, Apple notified the European Commission under Article 14 of the Digital Markets Act that it would, through a subsidiary, acquire certain assets of Sonera and offer jobs to and hire certain Sonera employees. The deal value was not disclosed and neither party has announced it; May 8 is the filing date, and no closing date has been made public. The Commission describes Sonera as a company developing chip-scale magnetic sensors. Founded in 2018 in Berkeley, California, as a University of California, Berkeley spinout, Sonera builds acoustically driven ferromagnetic resonance magnetic sensors that operate at room temperature and has raised about $20 million.

The study asks whether adding closed-loop BCI exoskeleton training to conventional rehabilitation improves lower-limb recovery in stroke patients. The retrospective cohort plans to enroll 58 patients in a closed-loop training group and 57 in a conventional rehabilitation group, with the primary endpoint being change in FMA-LE score from baseline to week 6. Secondary outcomes include motor imagery-related EEG features, the 10-Meter Walk Test and the Berg Balance Scale, indicating the researchers want to track both walking function and the brain signals themselves. The trial is self-funded by the research team and has not yet begun recruiting.

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.

About 70% to 80% of stroke survivors cannot live independently because of physical disability, and regaining walking function is central to changing that. This observational, cross-sectional study plans to enroll 200 stroke patients and 200 healthy controls, collecting EEG, fNIRS, sEMG, fMRI and other central and peripheral physiological signals alongside clinical measures such as Facial Action Units, the Berg Balance Scale and Fugl-Meyer motor function. The goal is a reusable non-invasive BCI dataset for stroke rehabilitation research. First enrollment is set for October 1, 2026.

To move from lab prototypes to long-term clinical systems, implantable brain-computer interfaces must place thousands to millions of electrodes several millimeters to centimeters deep in brain tissue without heating it by more than about 1 degree Celsius. This review benchmarks inductive, mid-field, RF, ultrasonic, magnetoelectric, optical, UWB and electro-quasistatic wireless links against three clinical axes (depth, size and data rate), noting that almost every clinically relevant implant is weakly coupled, with coupling coefficients of only 10^-3 to 10^-1. Within a communication budget of about 10 mW, narrowband high-Q links suit power transfer and low-speed data, but at 1-10 nJ/b they cannot deliver the more than 10 Mbps to tens of Gbps uplinks that interfaces with a thousand or more channels require. The study is a preprint and has not been peer reviewed.

Researchers have proposed a compact hybrid deep learning model for classifying four-class motor imagery EEG signals. Combining spatial convolutional filtering, bidirectional temporal modeling and an attention mechanism, the end-to-end model reached a mean accuracy of 83.89% on the public BCI Competition IV Dataset 2a, outperforming conventional baselines. The authors say bidirectional temporal modeling and attention weighting make motor imagery classification more robust, which could help BCIs assist patients with motor disabilities, and that the model offers an efficient option for decoding in resource-constrained settings.

Two participants typed Vietnamese at 4.95 and 3.45 characters per minute using motor imagery EEG in a pilot test of BCI-vSpeller, a speller built around a custom virtual keyboard of more than 160 selectable keys covering characters, tone marks and special symbols. Researchers from VNU University of Engineering and Technology in Hanoi, reported the findings in Technology and Disability. BCI spellers let users enter text by controlling an interface with mental signals, an approach aimed at people with severe speech and mobility impairments.

Motor attempt, meaning a patient's effort to move a paralyzed limb, was the intent-inducing modality most consistently tied to significant therapeutic effects in an umbrella review of 17 meta-analyses of brain-computer interface systems for stroke motor recovery, published in Symmetry on September 4, 2026 with a literature search cutoff of June 30, 2026. Electrical stimulation was a consistently effective feedback type, while robot-assisted and visual feedback gave inconsistent results, and higher weekly session frequency and moderate session durations of about 20 to 60 minutes were linked to consistent recovery. Combining motor attempt with electrical stimulation may yield greater benefits, the authors suggest.

Speech imagery (SI) brain-computer interface results may be hard to reproduce, a University of Essex team reports. When the researchers re-ran published decoding pipelines, classification accuracy averaged 11.25 percentage points below the original reports, with gaps ranging from 2% to 39%; in a replication analysis, only 36% of SI participants cleared the threshold for statistical significance, against 91% in motor imagery (MI) datasets. Published in the Journal of Neural Engineering on September 4, 2026, the study is the first to assess both the reproducibility and the replicability of SI decoding. Every SI study evaluated was missing methodological details, and the authors conclude that SI's feasibility as a practical BCI paradigm may have been overestimated, a warning for clinical applications and follow-up research that rely on it.