EEG and Brain-Computer Interfaces

This study shows that tagging frequency affects neural responses and cognitive performance in attention tasks using SSVEPs and ERPs.

This study examines how attentional load affects intracortical brain-computer interface (iBCI) performance during dual-tasking, finding robust performance but individual variability.

This paper introduces a text-sequence stimulation paradigm for ear-EEG BCIs, achieving higher information transfer rates and reduced BCI illiteracy compared to conventional luminance-modulated SSVEP methods.

This study evaluates how large language models improve P300 speller performance, showing up to 75% gains in typing speed and approaching theoretical limits.

This paper decodes emotion from EEG during overt and imagined vocalisation, finding that involuntary facial muscle activity contaminates EEG and contributes to emotion decoding.

This paper classifies expert-confirmed interictal epileptiform discharge epochs using EEG and ECG data, finding that ECG features improve categorization accuracy.

This paper compares Pearson correlation and mutual information estimators for analyzing neural evoked responses, identifying parameter settings and trade-offs for reliable similarity measures.

CORSICA suppresses cochlear implant artifacts in speech-evoked EEG data using cross-correlation with speech stimuli, outperforming alternative methods with minimal manual intervention.

This study uses EEG and machine learning to classify meditation styles and mind-wandering, showing high accuracy within individuals but poor generalization across subjects.

The paper uses EEG data and support vector machines to classify neural responses to words and images, finding higher accuracy for images than words.

This paper introduces a 3D CNN with a trainable CWT layer and BiCL pre-training for sub-second seizure detection, achieving >95% accuracy on EEG data.

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

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.

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.

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.

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

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

This paper develops a cross-subject neural-to-phoneme decoder for speech BCIs, achieving performance comparable to within-subject models through shared space alignment and hierarchical GRU decoding.

This study shows that personalized EEG neurofeedback using deep neural networks improves cognitive performance in adults, with significant gains in reasoning tasks and neural connectivity.

This paper introduces a cortex-anchored sensor-space basis for event-related EEG using forward-projected Laplace-Beltrami eigenmodes, showing improved reconstruction efficiency and reliability compared to spherical harmonics and PCA/ICA bases.

This study decodes speech and grasp from neural activity in sensorimotor cortices of tetraplegic participants, showing overlapping neural populations and reconfigured connectivity between tasks.

This study compares Gabor-based and classical flicker for SSVEP BCIs, finding Gabor flicker more comfortable at low frequencies and plain flicker better at high frequencies, with optimal performance when matched.

This paper presents a simulation framework to evaluate EEG source localisation methods by generating biologically plausible seizure dynamics and EEG signals with known ground truth.

This study evaluates if brain and muscle synergies improve decoding performance in implanted brain-machine interfaces (iBMIs) using dimensionality reduction techniques, finding that they do not enhance performance or generalization.

This paper introduces a variational autoencoder for detecting seizure onset phases in SEEG data, achieving high recall and interpretable latent features.

A paralyzed man with ALS used a long-term intracortical BCI for over two years to communicate, control a computer, and work independently.

sEEG-Suite provides a semi-automated pipeline for sEEG contact localization and anatomical labeling within Brainstorm, improving accuracy and efficiency in epileptic network mapping.

This paper improves seizure forecasting in drug-resistant epilepsy by using multiscale predictive modeling of iEEG features and seizure risk, achieving a 51% increase in pseudo-prospective accuracy.

sBOSC identifies neural oscillations in electromagnetic brain signals by detecting oscillatory episodes at their sources with high accuracy.