EEG and Brain-Computer Interfaces

This study compares TRF estimation methods for decoding auditory attention from EEG data using a standardized dataset.

The paper reanalyzes an open MEG/EEG dataset using MNE to compare different analysis strategies and provide best practices for group studies.

This paper demonstrates that a Latte Panda computer can collect EEG data reliably and portably, comparable to a laptop, enabling more mobile EEG experiments.

This study examines motion artifacts in infant and adult EEG during naturalistic activities, finding distinct topographical and spectral patterns in infants compared to adults.

This paper demonstrates a neural critic that classifies reward value from motor cortical activity with high accuracy, aiming to improve brain machine interfaces.

The paper describes a protocol for integrating anatomical and electrophysiological human intracranial EEG data using an open-source toolbox, enabling rapid and reproducible analysis.

This study compares methods for inter-subject decoding of motor imagery from MEG and EEG, finding that multi-task learning with logistic regression and l2,1-norm regularization achieves the best accuracy when trained on motor imagery data.

This paper challenges bipolar referencing in intracranial EEG and proposes ICA as a more effective method for isolating local brain activity.

This paper introduces BC-VARETA, a method for estimating brain sources and connectivity from M/EEG data using a frequency domain approach and sparse modeling.

This paper reviews multiway canonical correlation analysis (MCCA) for fusing brain signals across subjects to extract common components, with examples and discussion of its limitations.

This study uses low-cost consumer-grade EEG and machine learning to classify epilepsy in rural settings, achieving moderate cross-country performance.

DDTBOX is an open-source toolbox for multivariate pattern analysis of EEG data, enabling classification and regression of experimental variables through spatiotemporal decoding.

This paper presents a BCI system that enables paralyzed users to control a robotic assistant using thoughts, demonstrating adaptability and task completion in real-world scenarios.

The paper compares EEG/MEG methods for localization error, false positive activity, and false positive connectivity, finding that sLORETA and eLORETA have exact localization while others perform worse.

The paper introduces a method to reduce VEOG artifacts in EEG signals by using blink templates and a threshold correlation, effectively recovering ERP and EEG signals with minimal distortion.

The paper introduces techniques for preprocessing multichannel data to remove artifacts like drift, glitches, and ringing, improving data quality without discarding corrupted trials.

This study characterizes the ballistocardiogram (BCG) artifact in EEG signals during simultaneous fMRI, identifying its temporal and spatial dynamics and proposing insights for improved artifact removal.

This paper introduces a single-sensor automatic sleep-stage classification method using cross-frequency coupling estimates, achieving high accuracy and outperforming previous studies.

This paper introduces Canonical Correlation Analysis (CCA) to decode auditory brain responses and improve stimulus-response mapping for BCI applications.

This paper proposes a novel EEG source localization method that uses a graph-regularized low-rank representation model to improve task-related source reconstruction by eliminating spurious signals.

This paper demonstrates the use of LSTM networks for neural decoding in BCIs, showing improved accuracy and robustness compared to traditional linear models.

This study measures auditory P3 during outdoor cycling using mobile EEG, finding similar ERP topography and morphology but with reduced amplitude and changes in P2 and N1 components.

This paper introduces a new decoding method called distribution alignment decoding (DAD) that uses movement statistics to map neural activity to motor variables, achieving comparable or better performance than traditional supervised decoders in some cases.

This paper compares MEG source inversion algorithms and fit metrics to determine the laminar origin of neural activity, finding that sparsity-constrained methods and specific fit metrics improve discrimination accuracy.

This paper applies deep reinforcement learning to improve human sustained attention in a neurofeedback setting using simulated and real EEG data.

This study compares high-density EEG (SND) with standard density (ND) in capturing spatiotemporal aspects of early visual processing, finding SND provides more accurate and detailed neural information.

This paper investigates online auditory attention detection with neurofeedback, showing that training can improve performance and that stimuli correlate with AAD outcomes.

MatClassRSA is a Matlab toolbox for M/EEG classification and visualization of proximity matrices, offering tools for classification, RDM computation, and clustering.

This study presents a real-time technique using Mean Phase Coherence to predict epileptic seizures with a prediction horizon of 4-10 minutes, achieving success in 8 out of 10 test cases.

The paper identifies flaws in the use of information transfer rate (ITR) to evaluate brain-machine interfaces (BMIs) and discusses the limitations of ITR as a metric for BMI performance.