Northwestern Polytechnical University

EEG is easily contaminated by blinks, muscle activity and heartbeats, which can drag down how accurately a brain-computer interface reads intent. Researchers from the School of Automation and the School of Software at Northwestern Polytechnical University in Xi'an, northwestern China, built Diff-ADN, a single-channel denoiser that first reconstructs the signal according to contamination severity, then applies one diffusion-guided residual correction. It handles ocular, muscular, cardiac and mixed artifacts, reaching mean Pearson correlations with clean EEG of 0.839 to 0.936 at contamination levels from -7 to +2 dB. Across 4 public motor-imagery datasets, removing cardiac artifacts recovered 4.88 to 5.59 percentage points of decoding accuracy, up to 21.90 points in a single case, and a 2-second segment took 12.52 to 17.08 ms on the tested CPU. Better waveform reconstruction did not always translate into equal gains in decoding accuracy.

Researchers at Northwestern Polytechnical University propose SEDAT, a hybrid tokenizer for large EEG foundation models that folds squeeze-and-excitation spatial aggregation, data-adaptive Gaussian average filtering, instantaneous-frequency-guided segmentation and Fourier-domain resampling into a single efficient pipeline. Evaluated on 10 heterogeneous EEG datasets with four foundation models, LaBraM, EEGFormer, EEGPT and NeuroGPT, SEDAT improved classification by up to 15.3% over fixed-length windowing and by 1.2-4.6% over the next-best tokenizer, the authors report. The study was published in the Journal of Neural Engineering on September 1, 2026.

A collaborative study involving authors from Hangzhou Dianzi University and other institutions developed a three-dimensional helical stretchable neural probe and achieved 1024-channel signal acquisition in the pig cerebral cortex. The researchers also report single-unit recordings with long-term stability in the mouse deep brain, while flexible planar microelectrode arrays recorded subcutaneous EMG signals in mice. The probe is fabricated using planar microfabrication followed by thermally driven helical shaping, expanding wiring space and accommodating tissue motion. Mechanical simulations and cyclic stretching tests examined strain mitigation and electrochemical stability, respectively. These device and animal results do not establish long-term performance in humans.

A newly registered trial tests a brain-computer interface in post-stroke rehabilitation across 4 parallel arms: full cross-domain (emotion-cognition-motor) adaptive training, integrated cognitive and motor task training, single-dimension motor training, and conventional rehabilitation. Each arm plans 22 participants, 88 in total. It enrolls patients aged 30 to 80 with a first cerebral infarction or hemorrhage 3 months to 1 year earlier, unilateral hemiplegia, and upper-limb Brunnstrom stage II to IV. The primary outcome is a motor function score; secondary outcomes include EEG motor imagery event-related synchronization/desynchronization, prefrontal theta/alpha power ratio, and EEG-fNIRS coupling.