Papers

People with no brain-computer interface experience learned to move an on-screen cursor by imagined movement alone when the user and the algorithm were trained together. Carnegie Mellon University researchers led by Bin He used vibrations under the wrists to guide participants' mental strategies while an adaptive decoder reweighted the most informative brain signals. Across 31 untrained, able-bodied participants, average discrete accuracy reached 86% for one-dimensional and 77.5% for two-dimensional cursor control. Such non-surgical BCIs are cheaper and lower-risk than implants, but this one has so far been tested only in healthy volunteers on lab tasks.

Spotting a deviation of a few degrees can matter in precision tasks, yet conventional training that only reports whether an answer was right does little to sharpen sensitivity to small errors. Researchers at The University of Texas at Austin and the National Institute of Neurological Disorders and Stroke instead read the brain's own error signal, the error-related potential, from EEG and fed its presence or absence back to participants in real time. Over a five-day longitudinal study, this BCI training accelerated perceptual learning for 3° errors and improved performance for 6° errors compared with behavioral training alone, alongside a larger error positivity (Pe) amplitude.

Researchers developed a reproducible multi-layer brain-mimicking phantom that replicates the dimpling and rupture forces of rodent pia mater and dura mater during neural interface implantation, built from a 0.5% agarose skin layer, a 1.01% agarose pia layer and a pre-stretched PVC dura layer assembled in a simple benchtop process. Tested with a cantilever force system on microwires of 12–100 µm diameter (tungsten and stainless steel, various tip geometries) and segmented silicon probes, the phantom produced results within the range of in vivo Sprague-Dawley rat data with significantly lower insertion variability than in vivo testing. The authors say its modular design — layer thickness and stiffness can be tuned for different species or devices — makes it a low-cost early screening platform that can accelerate neural implant development while reducing animal use.

The study presents DSNet, a deep denoising structure-preserving neural encoding network that classifies privacy-preserving encoded EEG without decryption. Common spatial pattern (CSP) features are converted to irreversible neural codes — an irreversible neural transformation designed for privacy rather than a formal cryptographic guarantee — and two deep-learning architectures (a feedforward network and a recurrent RNN) classify in the encoded feature space. On public datasets, DSNet-NN exceeded 87% accuracy for every subject, outperforming the RNN variant and baselines while staying resilient to simulated privacy attacks; the study also integrated GPT-4 to generate clinical-style summaries from model outputs.