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

Read full text Summarise with VIRAT
Authors: J. Vengatachalam, M. Ezhilarasan
Cited by: 0
References: 21

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

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.

Fields of Study & Subjects

Emotion and Mood Recognition EEG and Brain-Computer Interfaces Gaze Tracking and Assistive Technology

Publication details

Journal / source
Advances in intelligent systems research/Advances in Intelligent Systems Research
Pages
441–461
Publication date
1 April 2026
Language
EN
Document type
Book chapter