Domain generalized feature embedded learning for calibration-free event-related potentials recognition
Author:
- 9 April 2026
- journal article
- research article
- Published by Springer Nature in Cognitive Neurodynamics
- Vol. 20 (1) , 77
Abstract
Event-related potentials (ERPs) play an important role for building EEG-based brain computer interfaces (BCIs). However, due to the complex and varied spatio-temporal characteristics of ERPs across subjects, data distribution across subjects a very important issue to be solved for constructing calibration-free BCIs. To achieve calibration-free ERPs recognition, we propose a Domain Generalized Feature Embedded Learning (DGFEL) method. First, we align the ERPs of each existed subject based on covariance centroids. Then, we enhanced the aligned samples based on xDAWN filter and extract spatio-temporal features. Finally, the spatio-temporal features are further generalized by the decomposed adversarial loss, and we construct a neural network embedding backbone to implement features generalization across subjects. The proposed method has been systematically validated on two benchmark EEG-based ERP datasets, and its classification performance surpasses several state-of-the-art methods as well as deep learning models. Moreover, it effectively captures robust features from existed source subjects, and can be generalized to new subjects without accessing target ERP samples. Our method therefore provides a novel selection to construct calibration-free ERP-BCIs.Keywords
Funding Information
- National Natural Science Foundation of China (62106049)
- Natural Science Foundation of Fujian Province (2022J01655)
This publication has 25 references indexed in Scilit:
- Dual regularized spatial-temporal features adaptation for multi-source selected cross-subject motor imagery EEG classificationExpert Systems with Applications, 2024
- Finding tau rhythms in EEG: An independent component analysis approachHuman Brain Mapping, 2024
- Window-Adjusted Common Spatial Pattern for Detecting Error-Related Potentials in P300 BCINeural Processing Letters, 2023
- Fuzzy temporal convolutional neural networks in P300-based Brain–computer interface for smart home interactionApplied Soft Computing, 2022
- Motor imagery EEG decoding using manifold embedded transfer learningJournal of Neuroscience Methods, 2022
- A new dynamically convergent differential neural network for brain signal recognitionBiomedical Signal Processing and Control, 2022
- Diagnosis of mild Alzheimer's disease by EEG and ERP signals using linear and nonlinear classifiersBiomedical Signal Processing and Control, 2021
- Sub-band target alignment common spatial pattern in brain-computer interfaceComputer Methods and Programs in Biomedicine, 2021
- A new combination: scale-space filtering of projected brain activitiesMedical & Biological Engineering & Computing, 2009
- Tikhonov regularized solutions for improvement of signal-to-noise ratio in case of auditory-evoked potentialsMedical & Biological Engineering & Computing, 2008