Chun-Shu Wei

A Comprehensive Benchmark of EEG-Based BCI Deep Learning Models for MCI and Dementia Classification

This paper benchmarks ten deep learning models for MCI and dementia classification using EEG data, finding that compact architectures can be competitive with larger models.

YOTO (You Only Think Once): A Human EEG Dataset for Multisensory Perception and Mental Imagery

The YOTO dataset provides high-resolution EEG recordings from 26 participants performing multisensory tasks, capturing neural responses to visual, auditory, and combined stimuli with self-reported vividness ratings.

Forecast Padding Enhances Accuracy and Robustness of EEG-Phase-Synchronized TMS

This paper introduces forecast padding to improve EEG-phase-synchronized TMS by reducing filter edge effects, enhancing stimulation accuracy and reducing deadlock rates.

SiamEEGNet: Siamese Neural Network-Based EEG Decoding for Drowsiness Detection

SiamEEGNet uses a Siamese neural network to detect drowsiness by analyzing relative EEG changes between baseline and time windows, outperforming existing methods in cross-subject scenarios.

OICNet: A Neural Network for Online EEG Source Separation using Independent Component Analysis

OICNet improves real-time EEG source separation by integrating non-Gaussianity and orthogonality constraints, outperforming existing methods in accuracy and efficiency.