Spatio-temporal Graph Transformer–based Graph Convolution Network for Human Emotion Recognition using EEG Signals

DOI

10.2991/978-94-6239-616-6_34How to use a DOI?

Keywords

human emotion recognition; brain activity; graph neural network; spatio-temporal graph transformer

Abstract

The brain–computer interface (BCI) is a branch of Human–Computer Interaction (HCI) enabling the communication between electronic devices like a mobile phone and a computer and the human brain. Emotions have a significant impact on human intelligence, perception, social interaction, and logical decision-making. Human Emotion Recognition (HER) is the process of knowing the emotional state of a human. The study of HER benefits from developments in computer science, psychology, modern neuroscience, and cognitive science. Electroencephalogram EEG signals are frequently used in non-medical settings such as entertainment, education, games, and monitoring. HER from EEG signals is essential in HCI and mental health diagnostics, but is often hindered by complex temporal dependencies, high noise, and dimensionality in the data. To resolve these problems, Machine Learning (ML) techniques have received significant interest amongst researchers. ML techniques are becoming increasingly important in classification jobs. To achieve this, the study presents a Spatio-temporal Graph Transform-based Graph Convolution Network for Human Emotion Recognition Using EEG Signals (STGTGCN-HER) technique. The proposed STGTGCN-HER model undergoes data preprocessing, feature extraction, classification, and hyperparameter tuning processes. By evaluating the sensitivity of several EEG parameters to emotional changes, the model explores how these factors affect emotion recognition, yielding more accurate and informative results. Experimental outcomes show that the STGTGCN-HER approach outperforms traditional methods, achieving superior accuracy and robustness in HER tasks.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - J. Vengatachalam
AU  - M. Ezhilarasan
PY  - 2026
DA  - 2026/03/31
TI  - Spatio-temporal Graph Transformer–based Graph Convolution Network for Human Emotion Recognition using EEG Signals
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 441
EP  - 461
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_34
DO  - 10.2991/978-94-6239-616-6_34
ID  - Vengatachalam2026
ER  -