Interpretable EEG Emotion Classification via CNN Model and Gradient-Weighted Class Activation Mapping
Brain Sciences · 20.08.2025 · 15 (8) · 886
DOI: 10.3390/brainsci15080886 ↗Kurz gefasst
Fachartikel in der Zeitschrift Brain Sciences, online erschienen am 20.08.2025. Verfasst von Yuxuan Zhao und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Natural Science Foundation, National Natural Science Foundation of China.
Abstract (Originalsprache)
Background/Objectives: Electroencephalography (EEG)-based emotion recognition plays an important role in affective computing and brain–computer interface applications. However, existing methods often face the challenge of achieving high classification accuracy while maintaining physiological interpretability.
Methods
In this study, we propose a convolutional neural network (CNN) model with a simple architecture for EEG-based emotion classification. The model achieves classification accuracies of 95.21% for low/high arousal, 94.59% for low/high valence, and 93.01% for quaternary classification tasks on the DEAP dataset. To further improve model interpretability and support practical applications, Gradient-weighted Class Activation Mapping (Grad-CAM) is employed to identify the EEG electrode regions that contribute most to the classification results.
Results
The visualization reveals that electrodes located in the right prefrontal cortex and left parietal lobe are the most influential, which is consistent with findings from emotional lateralization theory.
Conclusions
This provides a physiological basis for optimizing electrode placement in wearable EEG-based emotion recognition systems. The proposed method combines high classification performance with interpretability and provides guidance for the design of efficient and portable affective computing systems.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.
- School of Software and Microelectronics, Peking University, Beijing 102600, China.
- School of Mechanical Engineering, University of Science and Technology Beijing, Beijing 100083, China.
ORCID-Profile: Yuxuan Zhao, Yidao Ji, Bo Wang, Wei Wu
Förderung
- Beijing Natural Science Foundation
- National Natural Science Foundation of China
Zitieren
APA
Zhao, Y., Cao, L., Ji, Y., Wang, B., & Wu, W. (2025). Interpretable EEG Emotion Classification via CNN Model and Gradient-Weighted Class Activation Mapping. Brain Sciences, 15(8), 886. https://doi.org/10.3390/brainsci15080886
Vancouver
Zhao Y, Cao L, Ji Y, Wang B, Wu W. Interpretable EEG Emotion Classification via CNN Model and Gradient-Weighted Class Activation Mapping. Brain Sciences. 2025;15(8):886. doi:10.3390/brainsci15080886
BibTeX
@article{Zhao2025,
author = {Zhao, Yuxuan and Cao, Linjing and Ji, Yidao and Wang, Bo and Wu, Wei},
title = {Interpretable EEG Emotion Classification via CNN Model and Gradient-Weighted Class Activation Mapping},
journal = {Brain Sciences},
year = {2025},
volume = {15},
number = {8},
pages = {886},
doi = {10.3390/brainsci15080886}
}
EUVIMED