DenoFlow introduces a flow‑matching approach to denoise steady‑state visual evoked potential (SSVEP) EEG signals, avoiding direct mapping from noisy to clean data. It uses a field network that predicts the velocity of a straight path between contaminated and clean trials, integrating this field to produce denoised outputs while simultaneously training a classifier to supervise the result. Experiments on two public SSVEP datasets demonstrate that DenoFlow surpasses seven baseline denoising models in both signal fidelity and downstream decoding accuracy.
arXiv:2606. 08594v1 Announce Type: new Abstract: Deep learning EEG denoising architectures have scaled from tens of thousands to tens of millions of parameters, yet no prior study has isolated model capacity as the experimental variable or tested whether reconstruction metrics predict downstream neural-signal utility.
arXiv:2605. 14941v2 Announce Type: replace-cross Abstract: Electroencephalogram (EEG) signals are highly susceptible to artifacts, resulting in a low signal-to-noise ratio, which makes extraction of meaningful neural information challenging.
arXiv:2606. 24087v1 Announce Type: new Abstract: Reconstructing continuous speech from scalp electroencephalography (EEG) remains fundamentally challenging.
arXiv:2607. 05165v1 Announce Type: new Abstract: Non-invasive brain-to-speech decoding aims to restore communication to patients suffering from neurodegenerative disease, without the risks of neurosurgery.
arXiv:2606. 23707v1 Announce Type: cross Abstract: EEG spatial super-resolution (EEGSR) in real deployments is challenged by random channel missingness, unstable electrode quality, and changing visible-channel patterns caused by bad contacts or device variability.
arXiv:2607. 11530v1 Announce Type: new Abstract: Decoding continuous three-dimensional (3D) motor imagery (MI) using non-invasive electroencephalography (EEG)-based brain--computer interfaces (BCIs) remains challenging due to signal variability and residual decoding errors.
The study evaluates how low‑precision compression affects adversarial robustness in EEG decoders used for brain‑computer interfaces. Using BCI Competition IV‑2a data, the authors compare 32‑bit floating‑point models (EEGNet and ShallowConvNet) with models pruned to 50 % and quantized to INT8 via post‑training quantization (PTQ) or quantization‑aware training (QAT). Results show that accuracy‑preserving compression does not improve direct robustness—PGD attack accuracy remains 22–24 % across all variants—yet pruning reduces bidirectional transfer efficiency more than PTQ, indicating that robustness, transferability, and deployment efficiency are distinct properties of compressed EEG decoders.
arXiv:2609.36609v1 Announce Type: cross Abstract: Electroencephalography (EEG) analysis requires careful choices in preprocessing, statistical modeling, and machine learning because EEG signals are h...
arXiv:2610.08355v1 Announce Type: cross Abstract: Flow-matching models start from an isotropic Gaussian source, the standard choice when the correlation structure of the data is unknown in advance. F...
arXiv:2605. 29263v2 Announce Type: replace Abstract: Low-channel wearable electroencephalography (EEG) is attractive for long-term monitoring, but four frontal electrodes provide only a sparse and spatially biased view of distributed scalp activity.
Prism‑SQA is a neural framework that interprets surface electromyography (sEMG) quality assessment by separating each signal into a clean component and five contaminant-specific components using a U‑Net with bidirectional LSTM. Each contaminant is verified against canonical physiological signatures, allowing clinicians to see how specific noises affect quality. The resulting quality indices can be customized for different clinical contexts without retraining, and Prism‑SQA matches or surpasses current black‑box methods on both continuous and binary quality tasks.
arXiv:2606. 26519v1 Announce Type: new Abstract: Large language models (LLMs) can make scientific software easier to use.