Newsfeed
Real-time intelligence on brain-computer interface funding, clinical trials, research, and policy.
CNN-BiLSTM Hybrid Targets MI-EEG Decoding Gap
A CNN + bidirectional LSTM architecture shows robust MI-EEG decoding across 2- and 3-class tasks with subject-independent capability.
Read →Neuroprosthetics Market Hits $52.8B by 2034
Global neuroprosthetics market projected at $52.8B by 2034, growing 13.8% CAGR from $14.5B in 2024.
Read →DC-Coupled BCI Implants Face 6.4 nA Fault Risk
New paper proposes a 0.81 ms fault-detection circuit for DC-coupled neural implant front ends, addressing an underexamined tissue-safety gap.
Read →ProtoGIB-Workload Boosts EEG Cross-Subject F1 by 5.15%
ProtoGIB-Workload raises cross-subject EEG workload decoding Macro-F1 by 5.15% avg using graph bottleneck methods.
Read →BCI Electrode Materials Race: Carbon, Graphene, Silicon
From silicon Utah arrays to graphene and carbon fiber, BCI electrode materials shape signal quality, scarring, and longevity.
Read →SPD Learn Unifies Geometric Deep Learning for Neural Decoding
SPD Learn is a new open-source Python library unifying SPD matrix-based neural decoding with manifold-safe training.
Read →Physics-Constrained EEG Digital Twin Targets Closed-Loop BCI
A band-stratified port-Hamiltonian graph neural network builds a physics-grounded EEG digital twin for closed-loop neuromodulation design.
Read →MoDAl Cuts Speech BCI Word Error Rate to 21.6%
MoDAl framework cuts speech BCI word error rate from 26.3% to 21.6% by unlocking Broca's area signals.
Read →FRED EEG-fNIRS Imagined Handwriting Decoding 0.7952
FRED system hits 0.7952 overall accuracy on 4-class imagined handwriting via frequency-diverse EEG ensembles; fNIRS adds near zero.
Read →EEG Gait Decoder Hits 55% Closed-Loop Success at 70ms
A 2-block EEG BCI achieves 55.3% closed-loop gait initiation and 70.5ms prediction latency in pilot exoskeleton testing.
Read →SoniSpeech: 26.3% WER Open-Vocab Silent Speech Dataset
SoniSpeech debuts 34hrs of trimodal wearable silent speech data, benchmarking 26.3% WER on open-vocab recognition.
Read →Brain2Qwerty Hits 18% Error Rate Without Surgery
Meta AI's Brain2Qwerty decodes typed sentences from MEG at 18% CER in 35 healthy participants — no surgery required.
Read →Active Technology Raises RMB330M in China BCI Angel Record
Shanghai's Active Technology closed RMB330M in China's largest-ever BCI angel round, just 6 months after founding.
Read →32–128 Mbps Battery-Free BMI via RF Backscatter
New preprint proposes RF backscatter + near-field charging to hit 32–128 Mbps wirelessly without an implant battery.
Read →Octopus 16: 16-Electrode Wireless EEG BCI for $250
PiEEG's Octopus 16 packs 16 electrodes into a coin-sized wireless EEG device for $250, enabling hands-free game control via brain signals.
Read →Tether Evo: 3 Papers Target Cross-Subject BCI Decoding
Tether Evo's 3 peer-reviewed papers show one model can decode speech, vision, and music across multiple patients.
Read →Organoid Stimulation Shrinks Response from 93% to 10%
Repeated daily stimulation collapsed organoid network engagement from 93% to 10%, with a naive-control design isolating stimulation from maturation.
Read →EMG Gesture Decoding Hits 0.688 F1 Across Sessions
A montage-agnostic encoder retains 0.688 macro-F1 across EMG sessions vs. 0.540 for per-user LDA, without any recalibration.
Read →0.234 F1 Gain: EMG Encoder Skips Per-User Calibration
A montage-agnostic sEMG encoder beats per-user LDA by 0.234 macro-F1 on DB1, potentially ending calibration bottlenecks in myoelectric prosthetics.
Read →GRU Beats Mamba on Brain-to-Text '25 Benchmark
GRU decoders outperform Mamba hybrids on Brain-to-Text '25, hitting 12.62% PER and 21.19% WER.
Read →