Skip to main content

ORIGINAL RESEARCH article

Front. Psychiatry
Sec. Digital Mental Health
Volume 16 - 2025 | doi: 10.3389/fpsyt.2025.1494369
This article is part of the Research Topic Emotional Intelligence AI in Mental Health View all articles

Identifying Relevant EEG Channels for Subject-Independent Emotion Recognition Using Attention Network Layers

Provisionally accepted
Camilo E. Valderrama Camilo E. Valderrama *Anshul Sheoran Anshul Sheoran
  • University of Winnipeg, Winnipeg, Canada

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

    Electrical activity recorded with electroencephalography (EEG) enables the development of predictive models for emotion recognition. These models can be built using two approaches: subject-dependent and subject-independent. Although subject-independent models offer greater practical utility compared to subject-dependent models, they face challenges due to the significant variability of EEG signals between individuals. One potential solution to enhance subjectindependent approaches is to identify EEG channels that are consistently relevant across different individuals for predicting emotion. With the growing use of deep learning in emotion recognition, incorporating attention mechanisms can help uncover these shared predictive patterns. This study explores this method by applying attention mechanism layers to identify EEG channels that are relevant for predicting emotions in three independent datasets (SEED, SEED-IV and SEED-V). The model achieved average accuracies of 79.3% (CI: 76.0-82.5%), 69.5% (95% CI: 64.2-74.8%) and 60.7% (95% CI: 52.3-69.2%) on these datasets, revealing that EEG channels located along the head circumference, including F p 1 , F p 2 , F 7 , F 8 , T 7 , T 8 , P 7 , P 8 , O 1 , and O 2 , are the most crucial for emotion prediction. These results emphasize the importance of capturing relevant electrical activity from these EEG channels, thereby facilitating the prediction of emotions evoked by audiovisual stimuli in subject-independent approaches.

    Keywords: emotion recognition, Electroencephalogram, Affective Computing, deep learning, attention mechanism, EEG signal processing

    Received: 10 Sep 2024; Accepted: 08 Jan 2025.

    Copyright: © 2025 Valderrama and Sheoran. 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: Camilo E. Valderrama, University of Winnipeg, Winnipeg, Canada

    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.