Related Experiment Video
Updated: Jun 7, 2025
08:45
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
Published on: October 24, 2012
14.6K
A class alignment network based on self-attention for cross-subject EEG classification
Sufan Ma1, Dongxiao Zhang1, Jiayi Wang1
1School of Science, Jimei University, Xiamen, People's Republic of China.
Biomedical Physics & Engineering Express
|November 11, 2024
Summary
This study introduces a novel adversarial learning model to improve electroencephalogram (EEG) classification by aligning features across subjects while preserving class distinctions. The method enhances subject-specific EEG analysis by leveraging data from multiple individuals.
Area of Science:
- Neuroscience
- Machine Learning
- Biomedical Engineering
Background:
- Electroencephalogram (EEG) signal variability necessitates subject-specific models.
- Existing domain adaptation methods for EEG focus on domain alignment, potentially neglecting crucial class boundaries.
- This can lead to weak feature-category correlations in classification tasks.
Purpose of the Study:
- To propose a novel adversarial learning model for bolstering subject-specific EEG classification.
- To leverage information from multiple subjects to improve individual EEG analysis.
- To address limitations in current domain adaptation strategies by focusing on both domain alignment and class separability.
Main Methods:
- Extracting shallow and attention-driven deep features from EEG signals.
- Employing a class discriminator with a novel discrimination loss function to align same-class features and diverge different-class features across domains.
- Utilizing two parallel, harmonized classifiers for joint decision-making.
Main Results:
- The proposed model effectively leverages multi-subject data for enhanced individual EEG classification.
- The adversarial strategy successfully aligns features across domains while maintaining class separability.
- Experimental validation on two public EEG datasets demonstrated the model's superior efficacy.
Conclusions:
- The novel adversarial learning approach significantly improves subject-specific EEG classification.
- The method effectively balances domain alignment and class discrimination for robust feature extraction.
- This work offers a promising direction for developing more accurate and reliable EEG analysis tools.
