EUVIMEDEUVIMED entdecken
Crossref

Bridge Graph Attention Based Graph Convolution Network With Multi-Scale Transformer for EEG Emotion Recognition

Huachao Yan, Kailing Guo, Xiaofen Xing, Xiangmin Xu

IEEE Transactions on Affective Computing · 2024-10 · 15 (4) · 2042-2054

DOI: 10.1109/taffc.2024.3394873 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Affective Computing, 2024-10. Verfasst von Huachao Yan und 3 weiteren Autor:innen. Die Arbeit wurde bisher 65-mal zitiert (Crossref) und nennt 76 Literaturangaben. Gefördert von: Fundamental Research Funds for Central Universities, Basic and Applied Basic Research Foundation of Guangzhou, National Key R&D Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In multichannel electroencephalograph (EEG) emotion recognition, most graph-based studies employ shallow graph model for spatial characteristics learning due to node over-smoothing caused by an increase in network depth. To address over-smoothing, we propose the bridge graph attention-based graph convolution network (BGAGCN). It bridges previous graph convolution layers to attention coefficients of the final layer by adaptively combining each graph convolution output based on the graph attention network, thereby enhancing feature distinctiveness. Considering that graph-based networks primarily focus on local EEG channel relationships, we introduce a transformer for global dependency. Inspired by the neuroscience finding that neural activities of different timescales reflect distinct spatial connectivities, we modify the transformer to a multi-scale transformer (MT) by applying multi-head attention to multichannel EEG signals after 1D convolutions at different scales. MT learns spatial features more elaborately to enhance feature representation ability. By combining BGAGCN and MT, our model BGAGCN-MT achieves state-of-the-art accuracy under subject-dependent and subject-independent protocols across three benchmark EEG emotion datasets (SEED, SEED-IV and DREAMER). Notably, our model effectively addresses over-smoothing in graph neural networks and provides an efficient solution to learning spatial relationships of EEG features at different scales. Our code is available athttps://github.com/LogzZ.

Förderung

  • Fundamental Research Funds for Central Universities
  • Basic and Applied Basic Research Foundation of Guangzhou
  • National Key R&D Program of China
  • National Natural Science Foundation of China
  • Science and Technology Project of Guangdong
  • Natural Science Foundation of Guangdong Province
  • Guangzhou Key Laboratory of Body Data Science
  • Science and Technology Project of Zhongshan

Zitieren

APA

Yan, H., Guo, K., Xing, X., & Xu, X. (2024). Bridge Graph Attention Based Graph Convolution Network With Multi-Scale Transformer for EEG Emotion Recognition. IEEE Transactions on Affective Computing, 15(4), 2042-2054. https://doi.org/10.1109/taffc.2024.3394873

Vancouver

Yan H, Guo K, Xing X, Xu X. Bridge Graph Attention Based Graph Convolution Network With Multi-Scale Transformer for EEG Emotion Recognition. IEEE Transactions on Affective Computing. 2024;15(4):2042-2054. doi:10.1109/taffc.2024.3394873

BibTeX
@article{Yan2024,
  author = {Yan, Huachao and Guo, Kailing and Xing, Xiaofen and Xu, Xiangmin},
  title = {Bridge Graph Attention Based Graph Convolution Network With Multi-Scale Transformer for EEG Emotion Recognition},
  journal = {IEEE Transactions on Affective Computing},
  year = {2024},
  volume = {15},
  number = {4},
  pages = {2042--2054},
  doi = {10.1109/taffc.2024.3394873}
}
Kostenlos starten →