EEG and Brain-Computer Interfaces

EegFun.jl: A Julia Package Tutorial for EEG Analysis

EegFun.jl provides a Julia package for EEG analysis, offering tools for data import, filtering, ICA, epoch extraction, and ERP visualization with high performance and ease of use.

Neurofeedback Training on Motor Cancellation Enhances Peripheral but not Cortical Beta Band Oscillations

Frequency-Specific Operant Learning in Neurofeedback Reveals Distinct Cortical Mechanisms: Evidence from Double-Blind ERSP and ERP Dissociations

This study shows that SMR neurofeedback leads to durable resting-state alpha increases, while Beta training shows strong acute control but no consolidation, indicating distinct cortical mechanisms for different frequency bands.

Multi-modal Ensemble Approach for Decoding Player Intentions in Table Tennis

This paper predicts table tennis player intentions using EEG and pose data, showing that a multi-modal ensemble improves prediction accuracy compared to single-modal approaches.

An Open-Source End-to-End Pipeline for Large-Scale EEG-Based Brain Age Modelling

This paper presents an open-source pipeline for EEG-based brain age modeling using the TUEG dataset, evaluating multiple regression models and incorporating SHAP for interpretability.

Falsifiable substitution tests reveal task-structured neural evidence for auditory attention

The paper introduces a falsifiable framework to test whether neural decoders capture auditory attention by evaluating evidence across disjoint data and substitutions.

Classifier-guided Deep Oscillatory Neural Networks (cDONN) for capturing both Neural Dynamics and Behavior simultaneously

This paper introduces cDONN, a neural network that generates EEG signals and classifies behavior simultaneously, showing high fidelity in synthesized EEG data.

Leveraging Pretrained Vision Transformers for classifying Alcohol Use Disorder using Raw Resting-State EEG

This study uses EEGViT, a transformer-based model, to classify Alcohol Use Disorder from raw resting-state EEG data, achieving 56% accuracy with sex- and age-stratified results.

A generalizable speech neuroprosthesis

This paper introduces a multi-user transformer-based decoder for intracortical speech BCIs, achieving lower word error rates with less training data than individual models.

Preprocessing Decisions Affect the Precision of P50 Estimates in the Paired-Click Paradigm

This study evaluates how preprocessing decisions affect P50 estimates in the paired-click paradigm, finding that correction pipelines improve precision compared to rejection pipelines.

Capturing the developing brain in motion: A practical tutorial for recording mobile EEG in naturally moving children

This paper provides a practical tutorial on mobile EEG data collection and preprocessing for naturally moving children, including a dataset and pipeline.

APICE-Py: An Open-Source MNE-Python Pipeline for Scalable EEG Preprocessing

A Python/MNE port of the APICE infant EEG preprocessing pipeline flags more artifacts than the MATLAB original but gives similar ERP measurement error in neonates and 5-month-olds.

Noise Optimization of Basic Signal Component Extraction for Cryogenic and On-Scalp Magnetoencephalography (MEG)

This paper introduces a novel preprocessing method for MEG data using Fosters inverse with signal space separation to improve noise reduction and source localization.

Multi-Source Neural Activity Indices for EEG/MEG Localization: A Two-Stage Spatial Filtering Framework and Extension to MNE-Python

This paper introduces a two-stage spatial filtering framework for EEG/MEG source localization, extending MNE-Python with a novel family of multi-source neural activity indices that do not require target source covariance matrix knowledge.

Benchmarking Neural Decoders for Brain-Computer Interfaces and Neural Population Analysis

BEND-BCI benchmarks 23 neural decoding methods across multiple tasks and recordings, showing that accuracy alone does not determine the best decoder for practical use.

Decoding Agency-Related Neural States During Human-AI Interaction in Autonomous Driving Using EEG and Deep Learning

This study decodes agency-related neural states from EEG during human-AI interaction using deep learning, showing that low-frequency neural activity reflects perceived control.

Canonical Correlation Analysis and Multi-Channel Cardiography Improve Artefact Cleaning in Heartbeat-Locked Analyses

This paper introduces a canonical correlation approach for multi-channel cardiac artefact removal in EEG data and shows it outperforms traditional methods in reducing artefacts while preserving neural signals.

Shared latent representations of speech production for cross-patient speech decoding

This paper shows that speech BCIs can be trained on combined patient data by aligning neural data to a shared latent space, improving decoding performance compared to patient-specific models.

Brain-computer interface training fosters perceptual skills to detect errors

This study shows that real-time feedback on error-related potentials during perceptual training enhances error detection ability, outperforming conventional feedback methods.

Classification of Healthy People and Schizophrenics Using Time- Frequency Domain Features Extracted from Electroencephalogram Signals

This paper develops an automated schizophrenia diagnosis method using EEG signals by extracting time, frequency, and time-frequency features and achieving 100% accuracy with three classifiers.

Decoding and Characterizing the Intracranial Representation of Semantic Information

This study decodes semantic information from intracranial neural activity, achieving above-chance classification of semantic categories using high-gamma power features.

A Minimally Invasiveness Hybrid Brain-Computer Interface: A Distributed, Scalable and Evolvable Architecture for Whole Brain Access

This paper introduces a minimally invasive hybrid brain-computer interface that improves signal quality and scalability over existing non-invasive and invasive systems.

Electrocorticographic Network Feature Space Constriction as a Preictal Biomarker

The paper identifies preictal biomarkers in epilepsy by analyzing network features from electrocorticographic data and uses them to predict seizure onset with a Support Vector Machine.

Simple Geometric Recentering Rivals Deep Sequence Models for Cross-Session EEG Motor-Imagery Decoding

This paper benchmarks deep sequence models against geometric baselines for cross-session EEG motor-imagery decoding, finding that a simple geometric approach outperforms complex models.

Seamless interaction in VR: decoding user intent with eye gaze and passive brain-computer interfaces

This paper demonstrates real-time EEG decoding of interaction intent during dynamic VR gameplay using eye gaze and passive BCIs, showing above-chance accuracy in classifying approach-avoidance and affordance-related decisions.

Effects of EEG Preprocessing on Channel-Wise Attention and Effective Connectivity Alignment in Visual EEG Decoding

This study evaluates how EEG preprocessing affects attention mechanisms in visual EEG decoding, showing that comprehensive preprocessing improves artifact suppression without sacrificing accuracy.

Deep Learning Reveals Cross-Modal Neural Representations of Auditory and Visual Mental Imagery in MEG

This study uses MEG and machine learning to decode auditory and visual mental imagery, showing deep learning models can capture cross-modal neural representations even from non-task-relevant regions.

PyLossless: A non-destructive EEG processing pipeline

PyLossless provides a non-destructive EEG pre-processing pipeline that maintains data integrity and allows flexible artifact handling.

Brain2voice 2.0: High-performance voice synthesis brain-computer interface

Brain2voice 2.0 improves voice synthesis from neural signals, achieving 5.24% word error rate, 8x better than prior methods, enabling real-time intelligible speech for paralyzed individuals.

Learning-related population dynamics in right and left dorsal premotor cortex during typing skill acquisition

The paper shows that during typing skill acquisition using a BCI, neural population dynamics in the dorsal premotor cortex become more compact, with left hemisphere showing enhanced firing-rate modulation and generalization.