EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Attention-Based Transfer Enhancement Network for Cross-Corpus EEG Emotion Recognition

Zongni Li, Kin-Yeung Wong, Chan-Tong Lam iD

Sensors · 13.09.2025 · 25 (18) · 5718

DOI: 10.3390/s25185718 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 13.09.2025. Verfasst von Zongni Li und 2 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Applied Sciences, Macao Polytechnic University, Macao 999078, China. Hauptthemen laut MEDLINE: Electroencephalography, Emotions, Attention. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangxi Science and Technology Department, Guangxi Colleges and Universities Key Laboratory of Intelligent Software.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A critical challenge in EEG-based emotion recognition is the poor generalization of models across different datasets due to significant domain shifts. Traditional methods struggle because they either overfit to source-domain characteristics or fail to bridge large discrepancies between datasets. To address this, we propose the Cross-corpus Attention-based Transfer Enhancement network (CATE), a novel two-stage framework. The core novelty of CATE lies in its dual-view self-supervised pre-training strategy, which learns robust, domain-invariant representations by approaching the problem from two complementary perspectives. Unlike single-view models that capture an incomplete picture, our framework synergistically combines: (1) Noise-Enhanced Representation Modeling (NERM), which builds resilience to domain-specific artifacts and noise, and (2) Wavelet Transform Representation Modeling (WTRM), which captures the essential, multi-scale spectral patterns fundamental to emotion. This dual approach moves beyond the brittle assumptions of traditional domain adaptation, which often fails when domains are too dissimilar. In the second stage, a supervised fine-tuning process adapts these powerful features for classification using attention-based mechanisms. Extensive experiments on six transfer tasks across the SEED, SEED-IV, and SEED-V datasets demonstrate that CATE establishes a new state-of-the-art, achieving accuracies from 68.01% to 81.65% and outperforming prior methods by up to 15.65 percentage points. By effectively learning transferable features from these distinct, synergistic views, CATE provides a robust framework that significantly advances the practical applicability of cross-corpus EEG emotion recognition.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyEmotionsAttentionHumansAlgorithmsNeural Networks, ComputerWavelet Analysis

Stichwörter der Autor:innen

cross-corpusdomain adaptationemotion recognitionself-supervised learning

Autor:innen und Institutionen

  • Faculty of Applied Sciences, Macao Polytechnic University, Macao 999078, China.
  • Guangxi Key Laboratory of Machine Vision and Intelligent Control, Wuzhou University, Wuzhou 543000, China.

ORCID-Profile: Chan-Tong Lam

Förderung

  • Guangxi Science and Technology Department
  • Guangxi Colleges and Universities Key Laboratory of Intelligent Software

Zitieren

APA

Li, Z., Wong, K. Y., & Lam, C. T. (2025). Attention-Based Transfer Enhancement Network for Cross-Corpus EEG Emotion Recognition. Sensors, 25(18), 5718. https://doi.org/10.3390/s25185718

Vancouver

Li Z, Wong KY, Lam CT. Attention-Based Transfer Enhancement Network for Cross-Corpus EEG Emotion Recognition. Sensors. 2025;25(18):5718. doi:10.3390/s25185718

BibTeX
@article{Li2025,
  author = {Li, Zongni and Wong, Kin-Yeung and Lam, Chan-Tong},
  title = {Attention-Based Transfer Enhancement Network for Cross-Corpus EEG Emotion Recognition},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {18},
  pages = {5718},
  doi = {10.3390/s25185718}
}
Kostenlos starten →