Treffer: ACFSENet: an adaptive cross-frequency global sparse encoding network for end-to-end EEG emotion recognition.

Title:
ACFSENet: an adaptive cross-frequency global sparse encoding network for end-to-end EEG emotion recognition.
Authors:
Qi W; University of Chinese Academy of Sciences, Beijing, People's Republic of China.; Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, People's Republic of China., Wang X; University of Chinese Academy of Sciences, Beijing, People's Republic of China.; Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, People's Republic of China., Yang W; University of Chinese Academy of Sciences, Beijing, People's Republic of China.; Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, People's Republic of China., Wang W; University of Chinese Academy of Sciences, Beijing, People's Republic of China.; Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, People's Republic of China.
Source:
Biomedical physics & engineering express [Biomed Phys Eng Express] 2026 Jan 15; Vol. 12 (1). Date of Electronic Publication: 2026 Jan 15.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: IOP Publishing Ltd Country of Publication: England NLM ID: 101675002 Publication Model: Electronic Cited Medium: Internet ISSN: 2057-1976 (Electronic) Linking ISSN: 20571976 NLM ISO Abbreviation: Biomed Phys Eng Express Subsets: MEDLINE
Imprint Name(s):
Original Publication: Bristol : IOP Publishing Ltd., [2015]-
Contributed Indexing:
Keywords: cross-frequency modeling; deep learning; electroencephalogram (EEG); emotion recognition; sparse attention
Entry Date(s):
Date Created: 20260106 Date Completed: 20260116 Latest Revision: 20260116
Update Code:
20260119
DOI:
10.1088/2057-1976/ae33c7
PMID:
41494206
Database:
MEDLINE

Weitere Informationen

End-to-end EEG-based emotion recognition is attracting increasing attention due to its potential in human-computer interaction, mental health, and affective brain-computer interfaces (aBCIs). However, most existing methods overlook cross-frequency interactions in neural oscillations and suffer from high computational complexity, limiting their applicability in real-time or resource-constrained scenarios. To this end, we propose ACFSENet, a novel end-to-end neural architecture that integrates adaptive cross-frequency modeling with global sparse encoding. ACFSENet employs an adaptive frequency-aware mechanism to dynamically focus on subject- and task-specific local brain dynamics, thereby enhancing the flexibility of emotional representation. In addition, it incorporates a sparse attention mechanism with a temporal distillation structure to reduce computational complexity while preserving the ability to model long-range temporal dependencies. We evaluate ACFSENet using cross-block validation on three benchmark datasets: DEAP, SEED, and SEED-IV. Results demonstrate that ACFSENet outperforms state-of-the-art methods and achieves a favorable balance between recognition performance and computational efficiency.
(© 2026 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.)