EEG and Brain-Computer Interfaces

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

This study evaluates GRU and LSTM for seizure detection in animal EEG data from rats exposed to kainate or Soman, showing better performance than classical models.

This study reviews and analyzes neurofeedback training's impact on memory in healthy adults, finding small-to-moderate improvements with varying factors influencing effectiveness.

This paper applies information geometry methods to EEG data to detect third-order neural interactions using optimized binarization and surrogate data validation.

This paper investigates decoding inner speech using EEG and MEG, finding that silent reading can be decoded with moderate accuracy while inner speech tasks perform at chance level.

The paper introduces a task-driven EEG dataset with channel-level motion artifact annotations and demonstrates a hybrid CNN-Transformer model for artifact detection and classification.

This paper introduces a transformer-based model for EEG source localization that outperforms traditional and machine learning approaches across various noise and data conditions.

This paper decodes colour from EEG signals during natural vision using a neural network and shows that colour information is robustly represented even without semantic guidance.

GEDAI improves EEG denoising by removing artifacts without clean references, outperforming existing methods in simulations and enhancing neurobehavioral predictions.

This study demonstrates that covert attention can be reliably measured using RIFT on a 360Hz consumer monitor, expanding accessibility for cognitive neuroscience research.

This paper introduces SONIC, a benchmarking paradigm for BCIs, demonstrating an ITR of over 200 bps using an ovine model and the Connexus BCI.

This paper introduces STA-EEGNet, a deep learning model for cognitive workload detection using EEG signals, showing improved accuracy and interpretable insights into neural dynamics.

The paper introduces a lightweight physics-based sensor-fusion filter for real-time EEG denoising that improves downstream AI classification without requiring training.

This study investigates how preparatory activity in the human motor cortex encodes movement features like direction, curvature, and distance, and demonstrates its use for predictive brain-computer interface control.

This paper introduces a post-processing framework to improve real-time sleep staging reliability in neuromodulation by combining smoothing techniques and control logic.

This study uses Taguchi Design of Experiment to optimize saline solution composition for improving electrical coupling in a multi-electrode EEG sensor, finding Tween-20 as the dominant factor.

This paper introduces a self-supervised learning framework for EEG-based biomarker discovery of cognitive health, but finds poor predictive performance using plasma p-tau217 as a proxy.

This study develops a groove brain-music interface (G-BMI) using EEG to create personalized playlists that enhance the urge to move by incorporating real-time neurofeedback.

The paper develops a hybrid BCI system using EEG and EMG signals to control a hand exoskeleton for rehabilitation, achieving reliable classification of flexion and resting states.

The paper uses EEG phase slip rates and related biomarkers to identify differences in brain activity between novice Vipassana meditators and non-meditators during decision-making tasks.

CARACAS is an ECG-free tool for identifying cardiac independent components in EEG data, achieving high sensitivity and specificity compared to existing methods.

This paper evaluates deep learning methods for sleep stage classification from EEG signals, finding that LSTM-based models provide more consistent trustworthiness and calibration than EEGNet.

The paper evaluates correlation-based features for neural voice activity detection using ECoG signals from an ALS patient, finding they outperform traditional log-power features in long-term stability.

The paper introduces a source-level noise covariance model for resting-state MEG/EEG data, improving source reconstruction reliability by avoiding artificial baseline distortions.

This paper proposes using Schrödinger bridge to generate images from EEG by reversing noise accumulation, improving robustness to inter-subject variability compared to diffusion models.

The paper semi-automatically annotates ictal chirps in iEEG data from epilepsy patients and finds their spectro-temporal features correlate with seizure onset zones and surgical outcomes.

This paper decodes intended speech from a person with anarthria and locked-in syndrome using an intracortical brain-computer interface, showing that phonemes, words, and higher-order language units can be decoded above chance.

KenazLBM is a model that characterizes and predicts brain states from raw iEEG data, generalizing across subjects with heterogeneous recording channels.

Concept2Brain generates synthetic electrophysiological responses to text and pictures using a deep learning model, enabling reproducible EEG datasets and AI-driven brain activity modeling.

This study compares traditional and BOSC methods for sleep spindle detection, finding BOSC more accurate in identifying valid spindles and reducing false detections.