Electroencephalography (EEG) is crucial for monitoring brain activity in neuroscience and clinical applications. However, the multitude of channels recorded by scalp electrodes poses challenges, including impractical usage and high model complexity. This paper addresses the challenges of high dimensionality in EEG data and introduces an innovative EEG channel selection algorithm, LSvT-NI, based on model training and noise injection, achieving substantial reductions in channels, model size, and complexity while maintaining high classification accuracy. Validated through experiments on EEGNet and the BCI Competition IV 2a dataset, the algorithm proves beneficial for practical and cost-efficient scenarios. Specifically, experiments on the BCI Competition IV 2a dataset demonstrate that LSvT-NI with white noise and pink noise at 5dB SNR achieves a remarkable 77.3% and 72.7% reduction in channels, along with 11.7% and 11% reductions in model size, and 86.9% and 71.8% in computation complexity.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/EMBC53108.2024.10782774 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Phase slips extracted from derivatives of EEG data provide a deeper insight into the formation of cortical phase transitions.
Front Integr Neurosci
February 2025
Department of Engineering, Institute of Biomedical and Neural Engineering, Reykjavik University, Reykjavik, Iceland.
The phase slips are generally extracted from the EEG using Hilbert transforms but could also be extracted from the derivatives of EEG, providing additional information about the formation of cortical phase transitions. We examined this from the 30 s long, 256-channel resting state, eyes open EEG data of a 30-year-old male subject. The phase slip rates, PSR1 from EEG, PSR2 from the first-order derivative of EEG, and PSR3 from the second-order derivative of EEG, respectively, were extracted.
View Article and Find Full Text PDFAn Investigation of Pre-stimulus EEG for Prediction of Driver Reaction Time.
Biomed Phys Eng Express
March 2025
Faculty of Engineering and Computing, Dublin City University, Dublin 9, Dublin, IRELAND.
Driver drowsiness significantly contributes to road accidents worldwide, and timely prediction of driver reaction time is crucial for developing effective advanced driver assistance systems. In this paper, we present an EEG-based prediction framework that investigates the impact of different pre-stimulus time windows, frequency band combinations, and channel groups on driver reaction time estimation using data from a 90-minute sustained attention driving task. Our systematic evaluation using a publicly available dataset of 24 drivers reveals that a 2-second pre-stimulus window yields the lowest prediction error.
View Article and Find Full Text PDFThe examination of sleep patterns in newborns, particularly premature infants, is crucial for understanding neonatal development. This study presents an automated multi-sleep state classification approach for infants in neonatal intensive care units (NICU) using multiperspective feature extraction methodologies and machine learning to assess their neurological and physical development. The datasets for this study were collected from Children's Hospital Fudan University, Shanghai and consist of electroencephalography (EEG) recordings from two datasets, one comprising 64 neonates and the other 19 neonates.
View Article and Find Full Text PDFREGEEG: A Regression-Based EEG Signal Processing in Emotion Recognition.
IEEE J Biomed Health Inform
March 2025
Electroencephalograms provide a non-invasive and effective method for studying emotion recognition and developing Artificial Intelligence (AI) models to understand human behavior and decision-making processes. This study involved testing several machine learning classification kernels to develop an accurate emotion recognition model capable of classifying emotions stimuli such as "Boring," "Calm," "Happy," and "Fear" during gameplay. An emotion classifier was assessed using the publicly available database for an emotion recognition system based on EEG signals and various computer games (GAMEEMO).
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!