MEF-net: A generalized hybrid multi-entropy feature fusion neural network model for cross-subject EEG-based emotion recognition
Journal of King Saud University Computer and Information Sciences · 2026-04 · 38 (3)
DOI: 10.1007/s44443-025-00441-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of King Saud University Computer and Information Sciences, online erschienen am 28.01.2026. Verfasst von Jia Wen Li und 9 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Open Research Fund of Nursing Key Laboratory of Sichuan Province, Sichuan Science and Technology Program, Foundation of the 2023 Higher Education Science Research Plan of the China Association of Higher Education.
Abstract (Originalsprache)
Cross-subject emotion recognition based on multi-channel Electroencephalography (EEG) signals remains a significant challenge due to complexity, non-linearity, high dimensionality, temporal variability, and individual differences. This study proposes a generalized hybrid multi-entropy feature fusion neural network, MEF-Net, which first integrates five distinct entropy-based features: Differential Entropy (DE), Kullback–Leibler Divergence Entropy (KL), Cross Entropy (CS), Conditional Entropy (CE), and Joint Entropy (JE), to represent emotional dynamics from various statistical and information-theoretic perspectives. Then, each feature is fed into a dedicated branch of an Enhanced Depthwise Parallel Convolutional Neural Network (EDPCNN), specifically designed to exploit the spatial-frequency characteristics of multi-channel EEG signals. Finally, an ensemble voting method is applied to aggregate the classification outputs from the five branches for enhancing cross-subject classification performance. Extensive evaluations across three benchmark EEG emotional datasets (DEAP, SEED, and MAHNOB-HCI) demonstrate that MEF-Net outperforms existing methods, achieving classification accuracies of up to 98.58%, 99.82%, and 98.10% for two-class, three-class, and four-class tasks, respectively. Furthermore, ablation experiments show an accuracy improvement of 7.35%, indicating that MEF-Net performs superior cross-subject emotion recognition by effectively analyzing the multi-dimensional characteristics of EEG signals through complementary entropy fusion and a parallel deep learning architecture. Consequently, the proposed method offers a generalized solution applicable to cross-subject emotion recognition and establishes a novel direction for analyzing EEG signals in the field.
Förderung
- Open Research Fund of Nursing Key Laboratory of Sichuan Province
- Sichuan Science and Technology Program
- Foundation of the 2023 Higher Education Science Research Plan of the China Association of Higher Education
- Foundation of the Sichuan Research Center of Applied Psychology
- Guangdong Province Ordinary Colleges and Universities Young Innovative Talents Project
- Neijiang Philosophy and Social Science Planning Project
- Key Discipline Improvement Project of Guangdong Province
- Scientific Research Capacity Improvement Project of the Doctoral Program Construction Unit of Guangdong Polytechnic Normal University
Zitieren
APA
Li, J. W., Lin, W. B., Ling, C., Zhang, S., Hu, X. L., Hu, X. Y., Vai, M. I., Lv, J. J., Liu, X., & Chen, R. J. (2026). MEF-net: A generalized hybrid multi-entropy feature fusion neural network model for cross-subject EEG-based emotion recognition. Journal of King Saud University Computer and Information Sciences, 38(3). https://doi.org/10.1007/s44443-025-00441-4
Vancouver
Li JW, Lin WB, Ling C, Zhang S, Hu XL, Hu XY, et al. MEF-net: A generalized hybrid multi-entropy feature fusion neural network model for cross-subject EEG-based emotion recognition. Journal of King Saud University Computer and Information Sciences. 2026;38(3). doi:10.1007/s44443-025-00441-4
BibTeX
@article{Li2026,
author = {Li, Jia Wen and Lin, Wei Bin and Ling, Chen and Zhang, Shuang and Hu, Xiang Lei and Hu, Xiu Ying and Vai, Mang I. and Lv, Ju Jian and Liu, Xin and Chen, Rong Jun},
title = {MEF-net: A generalized hybrid multi-entropy feature fusion neural network model for cross-subject EEG-based emotion recognition},
journal = {Journal of King Saud University Computer and Information Sciences},
year = {2026},
volume = {38},
number = {3},
doi = {10.1007/s44443-025-00441-4}
}
EUVIMED