A temporal-spectral graph convolutional neural network model for EEG emotion recognition within and across subjects
Authors:
Open Access
- 18 December 2024
- journal article
- research article
- Published by Springer Nature in Brain Informatics
- Vol. 11 (1) , 1-18
Abstract
EEG-based emotion recognition uses high-level information from neural activities to predict emotional responses in subjects. However, this information is sparsely distributed in frequency, time, and spatial domains and varied across subjects. To address these challenges in emotion recognition, we propose a novel neural network model named Temporal-Spectral Graph Convolutional Network (TSGCN). To capture high-level information distributed in time, spatial, and frequency domains, TSGCN considers both neural oscillation changes in different time windows and topological structures between different brain regions. Specifically, a Minimum Category Confusion (MCC) loss is used in TSGCN to reduce the inconsistencies between subjective ratings and predefined labels. In addition, to improve the generalization of TSGCN on cross-subject variation, we propose Deep and Shallow feature Dynamic Adversarial Learning (DSDAL) to calculate the distance between the source domain and the target domain. Extensive experiments were conducted on public datasets to demonstrate that TSGCN outperforms state-of-the-art methods in EEG-based emotion recognition. Ablation studies show that the mixed neural networks and our proposed methods in TSGCN significantly contribute to its high performance and robustness. Detailed investigations further provide the effectiveness of TSGCN in addressing the challenges in emotion recognition.Keywords
Funding Information
- The National Natural Science Foundation of China (62007016, 62007016, 62007016, 61772440)
- the Collaborative Innovation Platform Project for Fuzhou-Xiamen-Quanzhou National Independent Innovation Demonstration Zone (2022-P-028)
- the Project of Industry-University-Research Collaborative Innovation in Fujian Province Universities (2022Y4004)
- the 2022 Hulunbuir City’s Special Key Project for Revitalizing City by Science and Technology (2022HZZX002)
This publication has 62 references indexed in Scilit:
- FuS-GCN: Efficient B-rep based graph convolutional networks for 3D-CAD model classification and retrievalAdvanced Engineering Informatics, 2023
- EEG-based cross-subject emotion recognition using multi-source domain transfer learningBiomedical Signal Processing and Control, 2023
- 4D attention-based neural network for EEG emotion recognitionCognitive Neurodynamics, 2022
- Minimum Class Confusion for Versatile Domain Adaptation2020
- Improving emotion recognition is associated with subsequent mental health and well-being in children with severe behavioural problemsEuropean Child & Adolescent Psychiatry, 2020
- Cross-Subject Emotion Recognition Using Deep Adaptation Networks2018
- Hierarchical Convolutional Neural Networks for EEG-Based Emotion RecognitionCognitive Computation, 2017
- Deep CORAL: Correlation Alignment for Deep Domain Adaptation2016
- Pleasure-arousal-dominance: A general framework for describing and measuring individual differences in TemperamentCurrent Psychology, 1996
- A GENERAL PSYCHOEVOLUTIONARY THEORY OF EMOTION1980