Gusa: Graph-Based Unsupervised Subdomain Adaptation for Cross-Subject EEG Emotion Recognition
IEEE Transactions on Affective Computing · 2024-07 · 15 (3) · 1451-1462
DOI: 10.1109/taffc.2024.3349770 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Affective Computing, 2024-07. Verfasst von Xiaojun Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 68-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, STI2030-Major Projects.
Abstract (Originalsprache)
EEG emotion recognition has been hampered by the clear individual differences in the electroencephalogram (EEG). Nowadays, domain adaptation is a good way to deal with this issue because it aligns the distribution of data across subjects. However, the performance for EEG emotion recognition is limited by the existing research, which mainly focuses on the global alignment between the source domain and the target domain and ignores much fine-grained information. In this study, we propose a method called Graph-based Unsupervised Subdomain Adaptation (Gusa), which simultaneously aligns the distribution between the source and target domains in a fine-grained way from both the channel and emotion subdomains. Gusa employs three modules, such as the Node-wise Domain Constraints Module to align each EEG channel and obtain a domain-variant representation, the Class-level Distribution Constraints Module, and the Emotion-wise Domain Constraints Module, to collect more fine-grained information, create more discriminative representations for each emotion, and lessen the impact of noisy emotion labels. The studies on the SEED, SEED-IV, and MPED datasets demonstrate that Gusa significantly improves the ability of EEG to recognize emotions and can extract more granular and discriminative representations for EEG.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- STI2030-Major Projects
- Ministry of Science and Technology of the People's Republic of China
- Guangdong Natural Science Funds for Distinguished Young Scholar
- Program for Guangdong Introducing Innovative and Entrepreneurial Teams
Zitieren
APA
Li, X., Chen, C. L. P., Chen, B., & Zhang, T. (2024). Gusa: Graph-Based Unsupervised Subdomain Adaptation for Cross-Subject EEG Emotion Recognition. IEEE Transactions on Affective Computing, 15(3), 1451-1462. https://doi.org/10.1109/taffc.2024.3349770
Vancouver
Li X, Chen CLP, Chen B, Zhang T. Gusa: Graph-Based Unsupervised Subdomain Adaptation for Cross-Subject EEG Emotion Recognition. IEEE Transactions on Affective Computing. 2024;15(3):1451-1462. doi:10.1109/taffc.2024.3349770
BibTeX
@article{Li2024,
author = {Li, Xiaojun and Chen, C. L. Philip and Chen, Bianna and Zhang, Tong},
title = {Gusa: Graph-Based Unsupervised Subdomain Adaptation for Cross-Subject EEG Emotion Recognition},
journal = {IEEE Transactions on Affective Computing},
year = {2024},
volume = {15},
number = {3},
pages = {1451--1462},
doi = {10.1109/taffc.2024.3349770}
}
EUVIMED