EUVIMEDEUVIMED entdecken
Crossref

JMS2A: Joint Multi-source Domain and Two-step Alignment Strategy for Cross-subject EEG Emotion Recognition

Cognitive Science Society 2025, Jingtao Du, Huanyu He, Yang Tian, Liying Yang

eScholarship (California Digital Library) · 18.06.2025

DOI: 10.48448/m1r8-s419 ↗

Kurz gefasst

Fachartikel in der Zeitschrift eScholarship (California Digital Library), erschienen am 18.06.2025. Verfasst von Cognitive Science Society 2025 und 4 weiteren Autor:innen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Emotion recognition based on electroencephalography (EEG) plays a significant role in brain-computer interface (BCI) applications. However, individual differences often hinder the generalization of emotion recognition methods to unknown subjects. To address this, we propose an unsupervised domain adaptive model with joint multi-source domain and two-step alignment strategy (JMS2A). The alignment strategy consists of two steps: (1) To capture the structured information from source domain, we combine multiple source domains into a mixed source domain. Simultaneously, a single source domain and the target domain are combined to form a pseudo-target domain, which is then indirectly aligned with the mixed source domain; (2) To extract latent class information from the target domain, we extend supervised contrastive learning to enable direct alignment between source and target domain. We evaluated JMS2A on the SEED and SEED-IV datasets, achieving accuracies of 95.30% and 86.55%, respectively. Experimental results demonstrate that our approach outperforms state-of-the-art methods. The source code is available at https://github.com/cccyangt/JMS2A.

Schlagwörter

EEG-based emotion recognitioncross-subject generalizationunsupervised domain adaptationsupervised contrastive learningindividual differencesbrain-computer interface

Zitieren

APA

2025, C. S. S., Du, J., He, H., Tian, Y., & Yang, L. (2025). JMS2A: Joint Multi-source Domain and Two-step Alignment Strategy for Cross-subject EEG Emotion Recognition. eScholarship (California Digital Library). https://doi.org/10.48448/m1r8-s419

Vancouver

2025 CSS, Du J, He H, Tian Y, Yang L. JMS2A: Joint Multi-source Domain and Two-step Alignment Strategy for Cross-subject EEG Emotion Recognition. eScholarship (California Digital Library). 2025. doi:10.48448/m1r8-s419

BibTeX
@article{2025,
  author = {2025, Cognitive Science Society and Du, Jingtao and He, Huanyu and Tian, Yang and Yang, Liying},
  title = {JMS2A: Joint Multi-source Domain and Two-step Alignment Strategy for Cross-subject EEG Emotion Recognition},
  journal = {eScholarship (California Digital Library)},
  year = {2025},
  doi = {10.48448/m1r8-s419}
}
Kostenlos starten →