A single Transformer-based decoder trained on the OpenBMI dataset classified eight EEG classes spanning motor imagery, P300, and SSVEP paradigms with 71.00% mean accuracy across 54 participants. Subject of Research: A unified Transformer architecture for decoding motor imagery, P300, and SSVEP EEG signals in…
A case-control study of 60 healthy adults found that four weeks of mirror therapy combined with shaping activities improved unilateral dexterity and reaction time of the non-dominant hand, with no significant between-group advantage on a motor learning test.
EPFL researchers have built a low-power implantable chip, LogSync, that extracts synchrony biomarkers across brain regions and decodes cognitive and emotional states in real time.
A new review finds that safety evidence for implanted brain-computer interfaces remains fragmented across small, hard-to-compare studies, and proposes a lifecycle framework for standardising how safety is assessed from implantation through end-of-use. News Source: Cassandra Pierce. (October 28, 2026). Implanted brain-computer interfaces…
1.1 Background and Problem Statement Physical Bandwidth Asymmetry: The transmission capacity of the output interface via limbs (motor cortex) is overwhelmingly insufficient compared to the speed of thought processing within the brain. Hyperfocus and Somatic Degradation Risk: When working memory is…
AUSTIN, Texas, October 26, 2026--Paradromics Inc., a neurotechnology company developing high-data-rate brain-computer interfaces to restore and enhance human capabilities, today announced that the U.S. Food and Drug Administration (FDA) has approved an amendment to the protocol for its Connect-One Early Feasibility Study,…
A subject-independent evaluation of single-channel EMG gesture classification finds that plain softmax confidence matches costly uncertainty quantification methods, with gains concentrated in the rest class. News Source: Denise Maddox. (October 28, 2026). Single EMG Electrode Gesture Control: Softmax Confidence Beats Costly Uncertainty…
SAN FRANCISCO, October 22, 2026--Subsense, an AI-native neurotechnology company developing non-surgical, nanoparticle-based brain-computer interfaces (BCIs), today announced that John P. Donoghue, PhD, has joined as a scientific advisor. Through his pioneering work on BrainGate, Donoghue helped show that people with paralysis could…
Casey Harrell, here at home in the summer of 2026, uses a brain-computer interface to communicate with his family. Regents of the University of California, Davis Casey Harrell lost his voice to ALS or amyotrophic lateral sclerosis. As a volunteer in…
- Firefly’s AI foundation model, being built on more than 200,000 standardized EEG/ERP brain scans, bolsters its long-term BCI growth opportunity - - With over 3,000 Versus headsets shipped, the platform generates commercial revenue as Firefly pursues higher long-term growth opportunities in the evolving…
Brain-computer interfaces from Neuralink, Synchron, Paradromics, Precision Neuroscience and academic labs decoding speech and movement, their trials and approvals.
An article joins this feed when it matches these terms. Each one is also a search of its own.