EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EEG-ERnet: Emotion Recognition based on Rhythmic EEG Convolutional Neural Network Model

Shuang Zhang, Chen Ling, Jingru Wu, Jiawen Li, Jiujiang Wang, Yuanyu Yu, Xin Liu, Jujian Lv, Mang I Vai, Rongjun Chen

Journal of Integrative Neuroscience · 28.08.2025 · 24 (8)

DOI: 10.31083/jin41547 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Integrative Neuroscience, online erschienen am 28.08.2025. Verfasst von Shuang Zhang und 9 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Numerical Simulation of Sichuan Provincial Universities, School of Mathematics and Information Sciences, Neijiang Normal University…. Hauptthemen laut MEDLINE: Emotions, Electroencephalography, Neural Networks, Computer, Recognition, Psychology. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangzhou Science and Technology Plan Project, Research Fund of Key Laboratory of Numerical Simulation of Sichuan Provincial Universities, Sichuan Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Emotion recognition from electroencephalography (EEG) can play a pivotal role in the advancement of brain-computer interfaces (BCIs). Recent developments in deep learning, particularly convolutional neural networks (CNNs) and hybrid models, have significantly enhanced interest in this field. However, standard convolutional layers often conflate characteristics across various brain rhythms, complicating the identification of distinctive features vital for emotion recognition. Furthermore, emotions are inherently dynamic, and neglecting their temporal variability can lead to redundant or noisy data, thus reducing recognition performance. Complicating matters further, individuals may exhibit varied emotional responses to identical stimuli due to differences in experience, culture, and background, emphasizing the necessity for subject-independent classification models.

Methods

To address these challenges, we propose a novel network model based on depthwise parallel CNNs. Power spectral densities (PSDs) from various rhythms are extracted and projected as 2D images to comprehensively encode channel, rhythm, and temporal properties. These rhythmic image representations are then processed by a newly designed network, EEG-ERnet (Emotion Recognition Network), developed to process the rhythmic images for emotion recognition.

Results

Experiments conducted on the dataset for emotion analysis using physiological signals (DEAP) using 10-fold cross-validation demonstrate that emotion-specific rhythms within 5-second time intervals can effectively support emotion classification. The model achieves average classification accuracies of 93.27 ± 3.05%, 92.16 ± 2.73%, 90.56 ± 4.44%, and 86.68 ± 5.66% for valence, arousal, dominance, and liking, respectively.

Conclusions

These findings provide valuable insights into the rhythmic characteristics of emotional EEG signals. Furthermore, the EEG-ERnet model offers a promising pathway for the development of efficient, subject-independent, and portable emotion-aware systems for real-world applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EmotionsElectroencephalographyNeural Networks, ComputerRecognition, PsychologyEvoked PotentialsBrain WavesHumansAdultYoung AdultBrain-Computer InterfacesMaleFemaleConvolutional Neural Networks

Stichwörter der Autor:innen

brain wavesconvolutional neural networkscross-validation studiesdeep learningelectroencephalographyemotions

Autor:innen und Institutionen

  • Key Laboratory of Numerical Simulation of Sichuan Provincial Universities, School of Mathematics and Information Sciences, Neijiang Normal University, 641000 Neijiang, Sichuan, China.
  • School of Artificial Intelligence, Neijiang Normal University, 641004 Neijiang, Sichuan, China.
  • School of Computer Science, Guangdong Polytechnic Normal University, 510665 Guangzhou, Guangdong, China.
  • ZUMRI-LYG Joint Lab, Zhuhai UM Science and Technology Research Institute, 519031 Zhuhai, Guangdong, China.
  • School of Mathematics and Computer Science, Northwest Minzu University, 730030 Lanzhou, Gansu, China.
  • Department of Electrical and Computer Engineering, University of Macau, 999078 Macau, China.

Förderung

  • Guangzhou Science and Technology Plan Project
  • Research Fund of Key Laboratory of Numerical Simulation of Sichuan Provincial Universities
  • 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 (Chengdu Medical College)
  • Neijiang Philosophy and Social Science Planning Project
  • Guangdong Province Ordinary Colleges and Universities Young Innovative Talents Project
  • Scientific Research Capacity Improvement Project of the Doctoral Program Construction Unit of Guangdong Polytechnic Normal University

Zitieren

APA

Zhang, S., Ling, C., Wu, J., Li, J., Wang, J., Yu, Y., Liu, X., Lv, J., Vai, M. I., & Chen, R. (2025). EEG-ERnet: Emotion Recognition based on Rhythmic EEG Convolutional Neural Network Model. Journal of Integrative Neuroscience, 24(8). https://doi.org/10.31083/jin41547

Vancouver

Zhang S, Ling C, Wu J, Li J, Wang J, Yu Y, et al. EEG-ERnet: Emotion Recognition based on Rhythmic EEG Convolutional Neural Network Model. Journal of Integrative Neuroscience. 2025;24(8). doi:10.31083/jin41547

BibTeX
@article{Zhang2025,
  author = {Zhang, Shuang and Ling, Chen and Wu, Jingru and Li, Jiawen and Wang, Jiujiang and Yu, Yuanyu and Liu, Xin and Lv, Jujian and Vai, Mang I and Chen, Rongjun},
  title = {EEG-ERnet: Emotion Recognition based on Rhythmic EEG Convolutional Neural Network Model},
  journal = {Journal of Integrative Neuroscience},
  year = {2025},
  volume = {24},
  number = {8},
  doi = {10.31083/jin41547}
}
Kostenlos starten →