Skip to main content

ORIGINAL RESEARCH article

Front. Hum. Neurosci.
Sec. Brain-Computer Interfaces
Volume 18 - 2024 | doi: 10.3389/fnhum.2024.1471634

Domain Adaptation Spatial Feature Perception Neural Network for Cross-Subject EEG Emotion Recognition

Provisionally accepted
Wei Lu Wei Lu 1,2Xiaobo Zhang Xiaobo Zhang 2,3*Lingnan Xia Lingnan Xia 1*Hua Ma Hua Ma 1*Tien-Ping Tan Tien-Ping Tan 2*
  • 1 Zhengzhou Railway Vocational and Technical College, Zhengzhou, Henan Province, China
  • 2 University of Science Malaysia (USM), Penang, Penang, Malaysia
  • 3 Jiangxi Vocational College of Finance and Economics, Jiujiang, China

The final, formatted version of the article will be published soon.

    Emotion recognition is a critical research topic within affective computing, with potential applications across various domains. Currently, EEG-based emotion recognition, utilizing deep learning frameworks, has been effectively applied and achieved commendable performance. However, existing deep learning-based models face challenges in capturing both the spatial activity features and spatial topology features of EEG signals simultaneously. To address this challenge, a domain-adaptation spatial-feature perception-network has been proposed for crosssubject EEG emotion recognition tasks, named DSP-EmotionNet. Firstly, a spatial activity topological feature extractor module has been designed to capture spatial activity features and spatial topology features of EEG signals, named SATFEM. Then, using SATFEM as the feature extractor, DSP-EmotionNet has been designed, significantly improving the accuracy of the model in cross-subject EEG emotion recognition tasks. The proposed model surpasses state-of-the-art methods in cross-subject EEG emotion recognition tasks, achieving an average recognition accuracy of 82.5% on the SEED dataset and 65.9% on the SEED-IV dataset.

    Keywords: Affective Computing, Electroencephalography, emotion recognition, Convolutional Neural Network, Graph attention network, Domain adaptation

    Received: 08 Aug 2024; Accepted: 04 Nov 2024.

    Copyright: © 2024 Lu, Zhang, Xia, Ma and Tan. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Xiaobo Zhang, Jiangxi Vocational College of Finance and Economics, Jiujiang, China
    Lingnan Xia, Zhengzhou Railway Vocational and Technical College, Zhengzhou, Henan Province, China
    Hua Ma, Zhengzhou Railway Vocational and Technical College, Zhengzhou, Henan Province, China
    Tien-Ping Tan, University of Science Malaysia (USM), Penang, 11800, Penang, Malaysia

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.