EEG and Brain-Computer Interfaces

High Variability Periods in the EEG: A New Temporal Metric that Reflects Brain States

The paper introduces a new EEG metric, High Variability Periods (HVPs), which reflects brain states by analyzing amplitude variability and shows differences across conditions.

Cortical dynamics following real-time MEG neurofeedback training of the speed of shifting spatial attention: a pilot study

This pilot study uses state-based neurofeedback to train participants to improve spatial attention shifting, showing generalized improvements in reaction times.

Brain-Controlled Electrical Stimulation Restores Continuous Finger Function

This study demonstrates that a brain-controlled functional electrical stimulation system can restore continuous finger function in a paralyzed monkey, achieving high success rates with minimal training.

Shaping Sounds with P300 Based Brain-Computer Musical Interface

This paper develops and tests a brain-computer musical interface that uses P300 waves to allow users to select and transform musical elements through attention.

Self-regulation of the brain's right frontal Beta rhythm using a brain-computer interface

This study shows participants could self-regulate their right frontal Beta rhythm using EEG neurofeedback, but no offline behavioral changes were observed.

qEEG Analysis in the Diagnosis of Alzheimers Disease; a Comparison of Functional Connectivity and Spectral Analysis

This study compares functional connectivity and spectral analysis using EEG data to detect differences between Alzheimer's patients and healthy controls, finding functional connectivity more effective in identifying AD-related brain activity patterns.

Predicting Working Memory performance based on specific individual EEG spatiotemporal features

This paper predicts individual working memory performance using EEG spatiotemporal features and shows that spatiotemporal characteristics can be used to customize WM tasks and optimize electrode use.

Seizure localisation with attention-based graph neural networks

This paper introduces a graph neural network with attention mechanism to localise seizure onset zones in epilepsy patients using intracranial EEG data, showing strong correlation with clinical reports.

Anomalous brain energy in old age by wavelet analysis of ERP during a Stroop task

The paper uses wavelet analysis of ERP data from a Stroop task to show that elderly with excess theta EEG activity use more energy in delta, theta, and alpha bands during stimulus categorization, potentially indicating a compensatory mechanism for cognitive demands.

Fast parametric curve matching (FPCM) for automatic spike detection

The paper introduces FPCM, a novel spike detection method for EEG/MEG data, showing robustness in low SNR conditions and reliable detection of interictal events.

Rethinking the Methods and Algorithms for Inner Speech Decoding - and Making them Reproducible

This paper evaluates methods for decoding inner speech from EEG data, achieving 35.20% accuracy for vowel classification and 29.21% for word classification, with reproducible code and data.

Evaluation of Long-Short Term Memory Networks for M/EEG Source Imaging with Simulated and Real EEG Data

This paper evaluates LSTM networks for M/EEG source imaging using simulated and real EEG data, finding higher accuracy compared to classical methods and alternative architectures.

Dual Passive Reactive Brain Computer Interface: a Novel Approach to Human-Machine Symbiosis

This paper introduces a dual passive-reactive BCI system for human-machine interaction, demonstrating 100% classification accuracy and 0.94 F1-score in a flight simulator setting.

Local interactions between steady-state visually evoked potentials at nearby flickering frequencies

The paper investigates how steady-state visually evoked potentials (SSVEP) responses are modulated by competing stimuli in human and monkey data, revealing local interactions between different flicker frequencies.

Harmonized-Multinational qEEG Norms (HarMNqEEG)

This paper develops multinational qEEG norms using Hermitian Riemannian methods, showing improved diagnostic accuracy for brain dysfunction and providing harmonization tools.

mulEEG: A Multi-View Representation Learning on EEG Signals

mulEEG is a multi-view self-supervised method for EEG representation learning that outperforms baselines and supervised training on sleep-staging tasks.

Decoding grasp and speech signals from the cortical grasp circuit in a tetraplegic human

This study decodes grasp and speech signals from high-level cortical areas in a tetraplegic human, showing that SMG and PMv can decode grasp intentions, while SMG also encodes speech.

Time-adaptive Unsupervised Auditory Attention Decoding Using EEG-based Stimulus Reconstruction

This paper introduces a time-adaptive unsupervised method for auditory attention decoding using EEG, showing it outperforms a time-invariant supervised approach.

Spatiotemporally Resolved Multivariate Pattern Analysis for M/EEG

This paper introduces STRM, a method for analyzing M/EEG data to infer spatiotemporal activity patterns and improve predictive accuracy in neuroscience tasks.

A multi-scale fusion CNN model based on adaptive transfer learning for multi-class MI-classification in BCI system

This paper introduces a multi-scale fusion CNN model with adaptive transfer learning for multi-class MI classification in BCI systems, achieving high accuracy with fewer training samples.

Concurrent separation of phase-locked and non-phase-locked activity

The paper introduces a new method to simultaneously separate phase-locked and non-phase-locked EEG activity, showing its effectiveness through simulations and experimental data.

Zapline-plus: a Zapline extension for automatic and adaptive removal of frequency-specific noise artifacts in M/EEG

Zapline-plus automatically and adaptively removes frequency-specific noise from M/EEG and LFP data by segmenting data, detecting noise peaks, and adjusting parameters for optimal cleaning.

Is sensor space analysis good enough? Spatial patterns as a tool for assessing spatial mixing of EEG/MEG rhythms

The paper demonstrates how spatial mixing in EEG/MEG data affects analysis in sensor space, using simulations and resting-state data to show challenges in disentangling overlapping rhythms.

The ZuCo Benchmark on Cross-Subject Reading Task Classification with EEG and Eye-Tracking Data

The paper introduces a machine learning benchmark for classifying reading tasks using EEG and eye-tracking data, providing a public dataset, baselines, and an evaluation platform.

A behavioral paradigm for cortical control of a robotic arm by freely moving rats in a one-dimensional two-target reaching task

This paper introduces a behavioral paradigm enabling freely moving rats to control a robotic arm in a one-dimensional two-target reaching task using primary motor cortex activity.

When the whole is less than the sum of its parts: maximum object category information and behavioral prediction in multiscale activation patterns

The paper compares decoding visual object categories using combined vs. individual EEG features, finding that individual multiscale Wavelet coefficients outperform combined features in prediction and behavioral explanation.

The Listening Zone of Human Electrocorticographic Field Potential Recordings

This study quantifies the spatial resolution of intracranial EEG recordings by analyzing signal correlation with distance, showing how electrode type, frequency, and referencing affect field potential spread.

Multi-channel deep learning with intracranial neurostimulation can localize seizure onset zones in humans

This paper develops a deep learning model to classify seizure onset zones using cortico-cortical evoked potentials from intracranial neurostimulation recordings.

"Thinking out loud": an open-access EEG-based BCI dataset for inner speech recognition

The paper presents an open-access EEG dataset for inner speech recognition to advance research on brain-computer interfaces.

Towards real-world neuroscience using mobile EEG and augmented reality

This paper combines mobile EEG and augmented reality to study neural responses to faces in real-world environments, finding increased low-frequency EEG activity for inverted faces across multiple tasks.