A temporal-spectral graph convolutional neural network model for EEG emotion recognition within and across subjects

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 recogniti...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui Li, Xuanwen Yang, Jun Lou, Junsong Zhang
Format: Article
Language:English
Published: SpringerOpen 2024-12-01
Series:Brain Informatics
Subjects:
Online Access:https://doi.org/10.1186/s40708-024-00242-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850134452902035456
author Rui Li
Xuanwen Yang
Jun Lou
Junsong Zhang
author_facet Rui Li
Xuanwen Yang
Jun Lou
Junsong Zhang
author_sort Rui Li
collection DOAJ
description 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.
format Article
id doaj-art-1ed1c21df0094643b1a49ee17798f00a
institution OA Journals
issn 2198-4018
2198-4026
language English
publishDate 2024-12-01
publisher SpringerOpen
record_format Article
series Brain Informatics
spelling doaj-art-1ed1c21df0094643b1a49ee17798f00a2025-08-20T02:31:42ZengSpringerOpenBrain Informatics2198-40182198-40262024-12-0111111810.1186/s40708-024-00242-xA temporal-spectral graph convolutional neural network model for EEG emotion recognition within and across subjectsRui Li0Xuanwen Yang1Jun Lou2Junsong Zhang3Brain Cognition and Computing Lab, National Engineering Research Center for E-Learning, Faculty of Artificial Intelligence in Education, Central China Normal UniversityBrain Cognition and Computing Lab, National Engineering Research Center for E-Learning, Faculty of Artificial Intelligence in Education, Central China Normal UniversityBrain Cognition and Computing Lab, National Engineering Research Center for E-Learning, Faculty of Artificial Intelligence in Education, Central China Normal UniversityBrain Cognition and Intelligent Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen UniversityAbstract 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.https://doi.org/10.1186/s40708-024-00242-xEEG signalAffective computingGraph neural networkCross-subjects
spellingShingle Rui Li
Xuanwen Yang
Jun Lou
Junsong Zhang
A temporal-spectral graph convolutional neural network model for EEG emotion recognition within and across subjects
Brain Informatics
EEG signal
Affective computing
Graph neural network
Cross-subjects
title A temporal-spectral graph convolutional neural network model for EEG emotion recognition within and across subjects
title_full A temporal-spectral graph convolutional neural network model for EEG emotion recognition within and across subjects
title_fullStr A temporal-spectral graph convolutional neural network model for EEG emotion recognition within and across subjects
title_full_unstemmed A temporal-spectral graph convolutional neural network model for EEG emotion recognition within and across subjects
title_short A temporal-spectral graph convolutional neural network model for EEG emotion recognition within and across subjects
title_sort temporal spectral graph convolutional neural network model for eeg emotion recognition within and across subjects
topic EEG signal
Affective computing
Graph neural network
Cross-subjects
url https://doi.org/10.1186/s40708-024-00242-x
work_keys_str_mv AT ruili atemporalspectralgraphconvolutionalneuralnetworkmodelforeegemotionrecognitionwithinandacrosssubjects
AT xuanwenyang atemporalspectralgraphconvolutionalneuralnetworkmodelforeegemotionrecognitionwithinandacrosssubjects
AT junlou atemporalspectralgraphconvolutionalneuralnetworkmodelforeegemotionrecognitionwithinandacrosssubjects
AT junsongzhang atemporalspectralgraphconvolutionalneuralnetworkmodelforeegemotionrecognitionwithinandacrosssubjects
AT ruili temporalspectralgraphconvolutionalneuralnetworkmodelforeegemotionrecognitionwithinandacrosssubjects
AT xuanwenyang temporalspectralgraphconvolutionalneuralnetworkmodelforeegemotionrecognitionwithinandacrosssubjects
AT junlou temporalspectralgraphconvolutionalneuralnetworkmodelforeegemotionrecognitionwithinandacrosssubjects
AT junsongzhang temporalspectralgraphconvolutionalneuralnetworkmodelforeegemotionrecognitionwithinandacrosssubjects