EEG and Brain-Computer Interfaces

This paper introduces a hybrid boundary element-finite element method to solve the EEG forward problem, combining the strengths of both methods to handle isotropic and anisotropic tissues.

This study shows that a single Alpha EEG-neurofeedback training session improves peripheral visual attentional performance in professional soccer players, with benefits lasting up to one month.

The paper assesses the feasibility of capturing P300 ERP responses in real-world settings using mobile EEG and eye-tracking during library searches.

This paper explores methods to improve EEG speech decoding by combining transcranial magnetic stimulation with delay differential analysis.

The paper uses machine learning on EEG data from hypnosis sessions to predict deep hypnosis levels in real time.

The paper validates age-stratified target ranges for P300 metrics using clinical data and compares them to research trends, showing consistency in age-related changes.

This paper benchmarks EEG artifact removal methods using a novel dataset and evaluates the effectiveness of Independent Component Analysis (ICA) in isolating artifacts.

This paper introduces a kernel-based nonlinear manifold learning method for EEG channel selection to distinguish Alzheimer's disease patients from healthy controls.

The paper validates in-clinic EEG alpha peak frequency measurements across age groups and confirms their stability over time, supporting their use for tracking cognitive changes.

The paper presents a hybrid EEG-EMG system to detect left and right steering actions in driving scenarios, showing improved performance through cross-correlation analysis.

This paper introduces N-interval Fourier Transform Analysis (N-FTA) to separate evoked and background activity in neural signals, identifying clinically relevant spectral bands in short latency median nerve evoked potentials.

The paper investigates how humans self-regulate cortical oscillations during brain-computer interface tasks, finding that basal ganglia-cortical connectivity plays a key role in this process.

HAPPILEE is a standardized automated pipeline for low-density EEG and ERP data processing, optimized for scalability and quality metrics.

This paper develops a multimodal AI system combining EEG and ECG for seizure detection, showing improved performance across out-of-distribution clinical datasets.

The paper evaluates an EEG-based focus detection system using Neurables Enten headphones and shows it accurately captures distractions across sessions and participants.

This paper develops an EEG-based neurofeedback system using SPLICE for depression treatment, showing reduced rumination in a NF group but no direct symptom reduction link.

This study compares a machine learning and a deep learning approach for classifying motor imagery EEG signals, finding that deep learning improves classification accuracy, especially for low performers.

The paper provides code and a pipeline for time-resolved multivariate pattern analysis of infant EEG data using linear SVM classification, showing reliable above-chance accuracy in both infants and adults.

The paper investigates the difference between stopping motor imagery (MI) and resting states, finding that MI termination can be detected faster and more accurately using Beta band features.

This paper introduces a spiking neural network for detecting auditory spatial attention from single-trial EEG data, achieving 90% accuracy with only 10% of the data.

This paper presents a GAN-based method to recover degraded signals in simulated long-term BCIs, maintaining decoder accuracy despite signal disruption.

The paper proposes a mix-bagging classifier with sliding window feature extraction and fuzzy discernibility matrix for motor-imagery EEG classification, achieving 92.14% accuracy on BCI Competition II Dataset III.

The paper compares temporal window-based and filter-bank approaches for motor-imagery EEG classification, finding that overlapping segments achieve the highest accuracy of 91.43% on BCI Competition II Dataset III.

This paper demonstrates an AI system for seizure detection that generalizes across continents, achieving human-level performance with significantly reduced annotation time.

The paper decodes imagined speech using low- and cross-frequency neural features from electrocorticography data, showing their effectiveness in perceptual speech spaces.

This study examines how neural population dynamics change in direct and indirect subpopulations during BMI learning, finding that coordination increases mainly in the direct subpopulation.

The paper introduces a group refactorization method for sleep EEG data to enable inter-individual analysis by aligning frequency factors across subjects.

DN3 is an open-source Python library for deep learning with neurophysiology data, enabling reproducible analysis and benchmarking across datasets, with applications in EEG-based biometrics.

This study investigates whether sleep and declarative interference affect motor imagery neurofeedback skill acquisition, finding no significant effects on ERD.

The paper compares EEG and MEG source spectra using BC-VARETA and finds no differences in reconstructed sources between the two modalities.