EEG and Brain-Computer Interfaces

A Novel Dual And Triple RSVP Paradigm For P300 Speller

This paper introduces and compares Dual and Triple RSVP paradigms for P300 speller systems, finding the Dual paradigm offers the best balance between information transfer rate and accuracy.

Convolutional Neural Networks for Decoding of Covert Attention Focus and Saliency Maps for EEG Feature Visualization

This paper evaluates CNNs for EEG decoding and introduces saliency maps to visualize model features, showing CNNs outperform LDA on high-dimensional data.

Shrinkage Classification for Overlapping Time Series: An interpretable method for mapping stimulus-differentiated evoked response

SCOTS maps brain function from neural time series by integrating spatio-temporal dependence through dimensionality reduction and classification, revealing category-specific neural activation patterns.

Comparison of Two-Talker Attention Decoding from EEG with Nonlinear Neural Networks and Linear Methods

This study compares two-talker attention decoding from EEG using nonlinear neural networks and linear methods, finding that a new architecture outperforms baselines and that wet and dry EEG systems yield comparable results.

Optimized visual stimuli for BCI with hessenberg decomposition based extreme learning machine

This study optimizes visual stimuli for BCIs by adjusting size, color, and background, and improves ELM performance using Hessenberg decomposition.

Deep learning with EEG spectrograms in rapid eye movement behavior disorder

This paper uses deep learning models on EEG spectrograms to diagnose and predict progression of REM Behavior Disorder, finding high accuracy in distinguishing patients who later develop Parkinson's or DLB from healthy controls.

Quantifying the individual auditory and visual brain response in 7- month-old infants watching a brief cartoon movie

The paper uses multivariate temporal response functions (mTRFs) to analyze continuous EEG responses in infants, showing robust individual and group-level neural tracking of auditory and visual stimuli.

Accurate Modeling of Brain Responses to Speech

The paper improves stimulus-response models for brain responses to speech using adaptive techniques and recurrent neural networks, achieving better classification performance in a match-vs-mismatch task.

A Comparison of Deep Neural Networks for Seizure Detection in EEG Signals

This paper compares ANN and CNN for seizure detection in EEG signals, finding ANN with dominant features achieves higher detection accuracy while CNN has better classification accuracy.

Comparison of Non-linear and Linear Models of Single Channel EEG in patients and normal subjects

The paper compares non-linear and linear models for predicting psychological traits from single-channel EEG signals in patients and normal subjects, finding non-linear models perform better.

Does Data Cleaning Improve Brain State Classification?

This study evaluates how data cleaning methods affect brain state classification in intracranial EEG and finds they reduce statistical power for detecting memory encoding.

Population subspaces reflect movement intention for arm and brain-machine interface control

The paper identifies shared and unique neural subspaces in motor cortex for arm and brain-machine interface control, revealing movement intention as a key representation.

Performance evaluation of inverse methods for identification and characterization of oscillatory brain sources: Ground truth validation & empirical evidences

This paper evaluates inverse methods for EEG/MEG source localization using simulated and empirical data, finding that eLORETA better controls false positives in distributed scenarios.

AUTOMAGIC: Standardized Preprocessing of Big EEG Data

Automagic provides standardized preprocessing and quality assessment for EEG data to address artifact contamination and improve replicability in large-scale studies.

Embodiment is related to better performance on an immersive brain computer interface in head-mounted virtual reality: A pilot study

This study compares neurofeedback performance in head-mounted virtual reality (HMD-VR) and computer screen environments, finding higher embodiment in HMD-VR correlates with better performance.

Towards an Objective Evaluation of EEG/MEG Source Estimation Methods: The Linear Tool Kit

The paper evaluates spatial resolution of EEG/MEG source estimation methods using resolution matrices and compares different techniques.

EECoG-Comp: An Open Source Platform for Concurrent EEG/ECoG Comparisons: applications to connectivity studies

The paper introduces EECoG-Comp, an open-source platform for analyzing EECoG data, and evaluates four ESI methods on a real dataset and simulations, highlighting their limitations.

Decoding of selective attention to continuous speech from the human auditory brainstem response

This paper decodes selective attention to speech from human auditory brainstem responses using statistical models, showing accurate attention focus decoding from short EEG recordings.

Decoding P300 Variability using Convolutional Neural Networks

The paper trains a convolutional neural network to decode P300 evoked responses from EEG data and shows it is sensitive to experimental variability and improves signal-to-noise ratio.

EEG-based Prediction of Cognitive Load in Intelligence Tests

This study predicts cognitive load during intelligence tests using EEG features and machine learning models, showing improved performance with subject-specific neural networks.

Amplifying the Neural Power Spectrum

The paper introduces a method to preprocess EEG signals by amplifying neural power spectra, improving decoding accuracy in visual stimulus experiments.

Asynchronous non-invasive high-speed BCI speller with robust non-control state detection

This paper introduces an asynchronous high-speed BCI speller with robust non-control state detection, achieving an average information transfer rate of 122.7 bit/min.

Functional disconnection of associative cortical areas predicts performance during BCI learning

This study shows that increased task-related activity and reduced connectivity between non-targeted brain regions predict better performance during BCI learning.

Comparison of EEG source reconstructed functional networks in healthy subjects elicited during visual oddball task

The paper compares EEG source reconstructed functional networks during a visual oddball task, finding that WT/PCA pairs yield better consistency and detect connectivity differences between target and non-target conditions.

The discrete logic of the Brain - Explicit modelling of Brain State durations in EEG and MEG

This paper introduces Hidden Semi-Markov Models (HSMM) to better model brain state durations in EEG and MEG data compared to traditional HMMs.

Analysis of miniaturization effects and channel selection strategies for EEG sensor networks with application to auditory attention detection

The paper evaluates whether optimizing wireless EEG sensor network topology can mitigate miniaturization effects in auditory attention detection.

Single Trial Decoding of Scalp EEG Under Natural Conditions

This study decodes mental states from scalp EEG under natural conditions using SVM classifiers and shows that small sets of de-noised data perform similarly to large sets of noisy data.

A Human-Machine Coupled System for Efficient Sleep Spindle Detection by Iterative Revision

The paper introduces a human-machine coupled system for efficient sleep spindle detection through iterative revision, achieving consistent results regardless of initial labeling.

Effect of head volume conduction on directed connectivity estimated between reconstructed EEG sources

This study evaluates how head volume conduction affects directional connectivity estimates from EEG source reconstruction using simulations and multiple connectivity measures.

Augmenting Quadriplegic Hand Function Using a Sensorimotor Demultiplexing Neural Interface

This study demonstrates that residual sensory signals from a paralyzed hand can be decoded from the motor cortex and used to enhance sensorimotor function via a closed-loop brain-computer interface.