中 / EN

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

Latest

September 2026

Single ECoG Implant Lets Paralyzed Participants Speak and Gesture Through an Avatar

A research team has used a single high-density electrocorticography (ECoG) implant, an electrode array placed on the brain's surface, to decode speech and gestures simultaneously in people with paralysis, ApplySci reported. When participants simply attempted to speak or gesture, a personalized virtual avatar spoke or moved accordingly, either both at once or separately. The researchers expected the brain signals during combined expression to be a simple sum of the two, but the data differed clearly from speech or gestures alone. Participants practiced a limited vocabulary of up to 10 gestures and 10 words or phrases.
Why it matters Most speech-decoding work restores talking alone; reading speech and gesture from one implant moves closer to natural communication, though the non-additive signals mean decoders must be trained on combined actions. The current standard, eye tracking, is slow, restrictive and physically tiring, the report noted, so even a small vocabulary points to room for improvement.

Neurotechnology Launches Mobile App for Computer-Free BrainAccess EEG Recording

Neurotechnology has released BrainAccess Mobile, a free Android app (Android 7 and later) that brings the core functions of its desktop software BrainAccess Board to phones and tablets. The app connects to one or more BrainAccess EEG devices over Bluetooth and handles device setup, signal acquisition, real-time viewing, electrode impedance checks, playback and data management, with data stored locally or streamed to a computer via the LSL protocol. The company says it suits outdoor state monitoring, synchronized multi-person recording and home sleep studies, but is not yet suited to experiments that require precise stimulus-response alignment, such as event-related potential and P300 paradigms, for which it still recommends a computer. The existing BrainAccess Mobile Lite will remain free.
Why it matters As portable EEG moves from the lab into everyday settings, dropping the laptop removes a practical barrier to recording outdoors and at home. The timing limitation the company itself acknowledges means the app does not yet extend to P300, one of the most widely used BCI paradigms.

Preprint: NEUROTOKEN Lifts EEG Attended-Speaker Accuracy by 9% to 16% in Noise

Researchers have proposed NEUROTOKEN, a single network that uses conditional flow matching to score candidate voices and identify, from EEG, which speaker a listener is attending to in a noisy room, the so-called cocktail-party problem. On the public KU Leuven, DTU and NJU datasets with 5-second windows, it raised per-segment accuracy by 9% to 16% over the strongest non-generative baseline and narrowed across-subject variance by about 3x. The authors also report that the 95% to 97% accuracies often cited for decoding attention direction fall by 17% to 45% once training and test trials are strictly separated. The work is a preprint and has not been peer reviewed.
Why it matters Hearing aids and BCIs need to know whose voice to amplify, and the paper's second finding matters as much as its gain: if direction-decoding scores collapse under strict trial splits, many published results in the field are likely optimistic. Validation so far is offline only, still some way from a working hearing aid.

BCI Stroke Rehab Aids Arm Recovery, Analysis Suggests Peak Near 48 Minutes

A meta-analysis of 26 randomized controlled trials covering 1100 stroke patients found that brain-computer interface (BCI) rehabilitation improved upper-extremity motor function compared with control interventions, but showed no significant benefit for lower-limb function or walking tests. A dose-response analysis suggested an inverted U-shaped relationship, with the peak effect at approximately 48 min per session.
Why it matters The dose-response analysis offers a research estimate of about 48 minutes per session, rather than an optimal duration established for every patient. The mean FMA-UE gain was 1.11 points, while lower-limb findings rest on just 2 studies with 78 patients.

NeuroXess Reports BCI-Assisted Object Creation and Household Device Control

NeuroXess reported that Xiao Jia, a participant with tetraplegia whose name is a pseudonym, used an implanted brain-computer interface with large AI models and 3D printing to turn brain-controlled sketches and text prompts into a physical figurine. He also helped create a personalized finger sleeve for tablet use. According to the company, he proposed ideas, compared options and made selections, while AI generated designs and digital models. In environmental interaction tasks, AI smart glasses identified objects and offered device-control options. After he expressed and confirmed his intention through the BCI, the system adjusted a bed and controlled lighting and household devices. These are application explorations involving this participant, not evidence of restored motor function.
Why it matters The report clarifies how the tasks are divided: the BCI conveys and confirms intentions, AI generates options or identifies environmental objects, and 3D printing or device-control systems carry out subsequent actions. This distinction helps show which decisions belong to the participant and which operations depend on external tools.

MetaIDNet Cuts EEG Color Vision Test Time by 70%

Color vision tests usually rely on what the subject reports, while a brain-computer interface can read the brain's response to color differences directly: the more two flickering light sources differ in perceived color, the stronger the steady-state visual evoked potential in the EEG. Existing systems sample color space evenly and repeat measurements at each point, which is accurate but slow. MetaIDNet, a closed-loop system, instead uses Gaussian process regression and a neural network to decide where to measure next. Offline, it made assessment 70% faster at the same accuracy; online, it improved accuracy by 40% at the same speed. The offline and online experiments involved only 10 and 8 participants.
Why it matters Objective EEG-based color vision testing has been held back by the time spent on repeated measurements to average out noise. Choosing sampling points on demand made MetaIDNet 70% faster offline and 40% more accurate online, but with 10 and 8 participants respectively, it needs larger studies before routine clinical use.

Review Maps BCI Use in Children With Brain Disorders

A review of brain-computer interface (BCI) research in children finds preliminary evidence that non-invasive systems are feasible for those above 5 years of age, but the supporting studies are small and short. It compares five paradigms (P300, motor imagery, SSVEP, fNIRS and hybrid systems) and four applications: communication aids, motor rehabilitation, ADHD attention training and autism social-emotional intervention. Evidence is firmer for communication and motor rehabilitation in cerebral palsy than for ADHD and autism.
Why it matters Most BCI research targets adults. This review focuses on children, whose developing brains, short attention spans and low tolerance for devices rule out simply reusing adult systems. Evidence is stronger for communication and motor rehabilitation in cerebral palsy, while ADHD and autism interventions still lack large, long-term data.

Speech BCIs Need Yardsticks Beyond Offline Accuracy, Review Argues

Speech brain-computer interfaces aim to restore communication by turning neural activity tied to speech, language or communicative intent into text, synthesized voice or avatar movements. This review argues they are not simple neural-to-text decoders but clinical systems that change over time, in which neural representations, recording hardware, decoding models, language models, feedback and the user's own learning interact. The authors say the next generation should be judged not only on offline accuracy but on stability across sessions, calibration burden, latency, the ability to signal uncertainty, usability and safeguards against decoding words a user did not mean to say. The paper is a preprint and has not been peer reviewed.
Why it matters Speech BCI progress has mostly been scored on decoding accuracy. This review shifts the question to daily use: whether performance holds from day to day, how long each calibration takes and whether the system might voice words the user did not intend. It also flags that language models can make output more fluent while drifting from the underlying neural signal. The paper is a preprint that has not been peer reviewed.

BrainNet Studio Puts 27 Brain Network Methods in One Open-Source Toolkit

Researchers have released BrainNet Studio, a single toolkit that takes brain network data from construction and feature extraction through predictive modeling and visualization. Brain networks map structural and functional links between brain regions, but most existing tools handle only static networks and miss how those links change over time. The toolkit bundles 27 algorithms spanning deep learning, graph neural networks and spatiotemporal sequence models, and uses a large language model to generate connectivity summaries that researchers can check. The developers say it can support cognitive neuroscience, exploratory brain disorder studies and brain-computer interface research. The work is a preprint and has not been peer reviewed.
Why it matters This is research software, not a device or clinical result. Its value lies in putting dynamic brain network modeling and graph neural network methods into one workflow, sparing labs from stitching analysis pipelines together. The code is open source, but the abstract reports no benchmark results and the paper has not been peer reviewed.

EEG Markers Track Brain Engagement in Stroke Action Observation Therapy

Can watching movements help stroke survivors retrain their arms? This scoping review screened 386 records and included 22 studies of upper-limb action observation therapy that measured EEG. Mu and beta rhythms over sensorimotor areas consistently desynchronized while patients watched movements, a sign that motor-related brain regions were engaged, and multi-week training produced sustained increases that often coincided with better upper-limb function scores. The authors see promise in BCI-based closed-loop therapy that uses EEG to adjust training in real time, but note that widely varying protocols make results hard to compare across studies.
Why it matters The review ties action observation therapy in stroke rehabilitation to measurable EEG markers and reports cortical and functional gains from BCI-driven training. Real-time personalized therapy is still a step away: the 22 studies used inconsistent task and stimulus designs, and the authors call for standardized protocols first.

© 2026 BCIwiki.com Digest Topics Tips Subscribe Revisions About