EUVIMEDEUVIMED entdecken
Crossref

Explainable multi-frequency and multi-region fusion model for affective brain-computer interfaces

Tao Wang, Rui Mao, Shuang Liu, Erik Cambria, Dong Ming

Information Fusion · 2025-06 · 118 · 102971

DOI: 10.1016/j.inffus.2025.102971 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information Fusion, 2025-06. Verfasst von Tao Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 85 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

An affective brain-computer interface (aBCI) has demonstrated great potential in the field of emotion recognition. However, existing aBCI models encounter significant challenges in explainability and the effective fusion of multi-frequency and multi-region features, which greatly limits their practical applicability. To address these issues, this paper proposes an explainable multi-frequency and multi-region fusion network (MFMR-FN), consisting of multi-frequency encoding and multi-region decoding networks. Specifically, in the encoding network, we leverage spectral graph theory and symmetric positive definite (SPD) matrix learning to adaptively encode EEG data into functional connectivity (FC) matrices with neurobiological information. Furthermore, a multi-frequency fusion algorithm, based on Riemannian geometry is designed to guide the network in achieving cross-frequency feature fusion. In the decoding network, we introduce a multi-region selection mechanism and a multi-scale Riemannian network, fusing brain network features from the whole brain, hemispheres, and local regions for coarse-to-fine emotion decoding. We conducted extensive experiments on the emotion recognition dataset (SEED) and the depression detection dataset (MODMA). The results show that MFMR-FN outperforms existing methods in multiple metrics and provides explainable FC features that reveal brain network patterns under different emotions and abnormal connectivity in depression. The proposed MFMR-FN is expected to improve the practicality and reliability of aBCIs in real-world and clinical applications.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, T., Mao, R., Liu, S., Cambria, E., & Ming, D. (2025). Explainable multi-frequency and multi-region fusion model for affective brain-computer interfaces. Information Fusion, 118, 102971. https://doi.org/10.1016/j.inffus.2025.102971

Vancouver

Wang T, Mao R, Liu S, Cambria E, Ming D. Explainable multi-frequency and multi-region fusion model for affective brain-computer interfaces. Information Fusion. 2025;118:102971. doi:10.1016/j.inffus.2025.102971

BibTeX
@article{Wang2025,
  author = {Wang, Tao and Mao, Rui and Liu, Shuang and Cambria, Erik and Ming, Dong},
  title = {Explainable multi-frequency and multi-region fusion model for affective brain-computer interfaces},
  journal = {Information Fusion},
  year = {2025},
  volume = {118},
  pages = {102971},
  doi = {10.1016/j.inffus.2025.102971}
}
Kostenlos starten →