EEG and Brain-Computer Interfaces

Frequency bands EEG Biomarkers for Dementia using Graph Neural Networks

This paper uses graph neural networks to classify EEG signals for Frontotemporal Dementia, achieving 76% accuracy with saliency maps highlighting key brain regions and frequency bands.

Generative enhancement of non-invasive datasets for motor brain-computer interface by synthesizing task-relevant neural signals

The paper enhances motor brain-computer interface datasets using a GAN to synthesize M1 neural signals, improving decoding performance by 10%.

How forgiving are M/EEG inverse solutions to noise level misspecification? An excursion into the BSI-Zoo.

This study evaluates how robust different BSI methods are to noise level misspecification using simulations and metrics like EMD.

The electro-MICA toolbox for integrating electrophysiology within multimodal imaging and connectomics workflows

electro-MICA projects electrophysiological features onto cortical surfaces using numerical solutions to electromagnetic equations, outperforming conventional models in iEEG validation.

Distorting anatomy to test MEG models and metrics

The paper uses deformable cortical surfaces to evaluate MEG source reconstruction algorithms and fit metrics.

Neuronal avalanches as a predictive biomarker of BCI performance- towards a tool to guide tailored training

This paper identifies neuronal avalanches as biomarkers to predict BCI performance and guide personalized training protocols.

Envelope analysis as a tool for identifying epileptic EEG patterns during the sleep-wake cycle in rats

This paper uses envelope analysis to identify epileptic EEG patterns in rats during the sleep-wake cycle, revealing morphological differences between epileptic and control groups.

A chill brain-music interface for enhancing music chills with personalized playlists

This study develops a neurofeedback system called C-BMI that uses EEG to create personalized playlists enhancing music-induced chills by integrating song preferences and neural responses.

Neural Networks and Foundation Models: Two Strategies for EEG-to-fMRI Prediction

This paper compares two strategies for predicting fMRI activity from EEG data: classical machine learning and deep learning models versus pre-trained large language models, showing promising results from both approaches.

Optimizing automated sleep stage scoring of 5-second mini-epochs: a transfer learning study

This paper optimizes an existing deep learning model for 5-second sleep stage scoring, achieving performance comparable to human and 30-second automated scoring, and demonstrating increased capture of sleep transitions.

Non-uniform effects of remaining field spread on the estimation of M/EEG activity and connectivity between regions of interest

This study quantifies non-uniform effects of remaining field spread on ROI activity and connectivity estimation in M/EEG using cross-talk functions.

An EEG-based Multi-Scale Hybrid Attention and Squeeze Network for objective taste assessment

This paper introduces MHASNet, a deep learning model for taste assessment using EEG signals, achieving high accuracy across five taste categories.

Using EEG to Detect Lapses in Sustained Attention to Moving Stimuli

This paper uses EEG and a hierarchical classification method to detect attentional lapses by predicting errors in a visual task based on neural decodability.

Assessing the robustness of deep learning based brain age prediction models across multiple EEG datasets

This study evaluates deep learning models for predicting brain age from EEG data across multiple datasets, finding that performance varies with dataset shifts and that certain hyperparameters improve generalization.

Feasibility of Stereo EEG Based Brain Computer Interfacing in An Adult and Pediatric Cohort

This study evaluates stereo EEG-based brain-computer interfacing (BCI) in adults and children, finding that overt motor BCI is more effective than imagery BCI, with performance varying by age and cortical region.

Predicting Spiking Activity from Scalp EEG

This study predicts spiking activity from scalp EEG by analyzing spectrotemporal features, showing that combining phase, amplitude, and coupling improves predictions compared to single features.

Preserved Neural Dynamics across Arm- and Brain-controlled Movements

This study compares neural dynamics during arm- and brain-controlled movements, finding preserved computational structures and manifolds in both conditions.

The Dominant Hand-Area Network: Task-Signal Mismatch and the Decoupling of BCI Skill from Global Efficiency in Postural Motor Imagery

This paper investigates how BCI decoding skill relates to global network integration during postural motor imagery, finding that skill is driven by local signal fidelity rather than global efficiency.

Comparing Methods for Mass Univariate Analyses of Human EEG: Empirical Data and Simulations

The paper compares mass univariate methods for EEG analysis using empirical data and simulations, finding cluster-based permutation tests are sensitive while permutation-based tmax is conservative.

Mithra: An Open-Source and Cross-Platform Visualization Toolbox for Human Intracranial Recordings

Mithra is a cross-platform visualization toolkit for intracranial recordings that enables systematic within- and across-subject electrode localization and analysis.

Impact of the pulse artifact on evoked activity in human wakefulness and sleep

This study assesses the impact of pulse artifacts on evoked potentials during wakefulness and sleep using two preprocessing pipelines in healthy volunteers.

MatClassRSA v2 release: A MATLAB toolbox for M/EEG classification, proximity matrix construction, and visualization

MatClassRSA v2 is a MATLAB toolbox for M/EEG classification, RDM computation, and visualization, offering updated modules and functionalities for cognitive neuroscience research.

Posterior Cortex Isolation Enhances Detection of Alpha Desynchronization During Sustained Attention

This paper shows that isolating posterior cortex in EEG improves detection of alpha desynchronization linked to sustained attention and mental fatigue.

Insular error network enables self-correcting intracranial brain-computer interface

This paper develops a self-correcting intracranial brain-computer interface (BCI) by integrating error-related neural activity from the insula and prefrontal cortex.

Decoding brain-wide signatures of uninformed choices for BCI assisted decision-making

This paper decodes brain signals to detect uninformed decisions and proposes a BCI to improve decision-making quality by alerting users.

Real-life ear-EEG Recordings of Auditory Responses to Ambient Sounds

This study measures auditory evoked potentials in real-life environments using ambient sounds and compares signal quality across different EEG recording setups.

Simulating Scalp EEG from Ultrahigh-Density ECoG Data Illustrates Cortex to Scalp Projection Patterns

This study simulates scalp EEG from ultrahigh-density ECoG data to show that scalp electrode activity reflects distributed cortical sources, not just local activity near the electrode.

Block-structured Bayesian source estimation model for magnetoencephalography signals

This study introduces a block-structured Bayesian model for MEG source estimation that integrates functional brain areas and inter-areal relationships, improving accuracy in localizing neural activity.

A Large Electroencephalogram Database of Freewill Reaching and Grasping Tasks for Brain Machine Interfaces

The paper presents a large EEG dataset of freewill reaching and grasping tasks for brain machine interfaces, capturing 6808 trials from 23 healthy adults.

Connecting a P300 speller to a large language model

This paper connects a P300 speller to a large language model to improve text generation accuracy and communication speed by leveraging contextual error correction.