EEG and Brain-Computer Interfaces

This paper introduces Burst c-VEP, a novel visual stimulus design for BCI that improves classification accuracy and user experience with minimal calibration data.

This paper introduces an inter-brain attention coupling method to detect learning-related attention in primary school students and finds it correlates with academic performance.

This study compares alpha, SSVEP, and gamma power in human EEG to determine their effectiveness in capturing attentional modulation, finding alpha and SSVEP are comparable while gamma is less effective for non-foveal stimuli.

The paper compares neural representations in motor cortex, prefrontal cortex, and striatum during brain-machine interface and manual reaching tasks in nonhuman primates.

This paper introduces a method to transform EEG data into a spectral representation using learned graphs for motor imagery decoding, showing improved performance over existing methods.

This paper transfers brain-computer interface decoders from monkeys to humans, showing that motor-related neural representations are consistent across species and reducing the need for extensive data.

The paper presents a scalable EEG hyper-scanning system for recording audience brain activity using low-cost components and custom software, achieving robust data alignment and performance in both lab and cinema settings.

This study improves motor-related ECoG BCI systems by using genetic feature selection and signal splitting to enhance accuracy and reduce prediction time.

YAEL streamlines electrode localization in iEEG by integrating all steps into a single GUI, enabling efficient and automated localization with high-quality visualization.

This paper proposes a hybrid deep learning model for automatic sleep staging using single-channel EEG signals, achieving high accuracy and F1-scores across sleep stages.

This study identifies optimal parameters for rapid invisible frequency tagging (RFT) using MEG, showing that stimulation frequency, patch size, and position significantly affect brain responses.

DISCOVER-EEG is an open, automated EEG pipeline that preprocesses, analyzes, and visualizes resting state EEG data to extract brain function features, tested on two large datasets.

This paper demonstrates a high-performance speech neuroprosthesis that achieves low word error rates and high decoding speeds using intracortical recordings from a person with ALS.

This study shows that fNIRS-based neurofeedback can modulate rTPJ activity and affect attention reorienting, with learning differences between up- and downregulation groups.

This study identifies biases in group-level EEG microstate analysis and proposes a paired analysis approach to reduce errors from subgroup topography differences.

This paper improves brain-computer interface decoding accuracy over time using Cycle-GAN and ADAN methods, outperforming linear methods with minimal data requirements.

This study shows that error-related potentials (ErrPs) encode both the magnitude of errors and individual perceptual thresholds through amplitude and latency, with implications for cerebellar contributions to performance monitoring.

This paper uses a recurrent neural network to reconstruct neural activity from MEG data, showing improved signal quality compared to existing methods.

This paper investigates whether decision confidence can be decoded from EEG signals post-stimulus and pre-response to enable a brain-computer interface for improving decision making.

The paper demonstrates remote EEG data collection using EmotivPRO Builder and EmotivLABS, showing a significant alpha power difference between resting state conditions.

This paper optimizes deep learning models for speech reconstruction from sensorimotor brain activity, achieving high word decoding accuracy and intelligible speech.

This paper applies quantum mechanics to EEG analysis, differentiating borderline personality disorder from schizophrenia by analyzing P3a and P3b components in single trial ERPs.

This paper examines optimal window size selection for EEG connectivity analysis in infants, adults, and dyadic pairs, finding that optimal sizes vary depending on the metric and dataset.

This study evaluates how anatomical accuracy and electrode positions affect EEG forward solutions, finding that SimNIBS provides more accurate results than MNE-Python and FieldTrip.

This paper introduces a bimodal EEG-fMRI dataset for inner-speech recognition, collected from four participants during inner-speech tasks.

The paper compares ten ESI methods using in-vivo EEG data to evaluate their accuracy and parameter sensitivity in localizing focal brain sources.

This study uses EEG and machine learning to show how neural representations of object features and locations dynamically update during attention shifts.

This study examines how task context affects brain-machine interface performance, finding that offline predictions are sensitive to context changes but online control remains stable.

This study introduces a novel explainability approach for rs-EEG deep learning classifiers, revealing spatio-spectral interactions in MDD diagnosis.

This study compares EEG patterns from real and imagined vibrotactile sensations on the right hand, finding similar ERD patterns in motor and somatosensory areas.