Cross-subject affective analysis based on dynamic brain functional networks

IntroductionEmotion recognition is crucial in facilitating human-computer emotional interaction. To enhance the credibility and realism of emotion recognition, researchers have turned to physiological signals, particularly EEG signals, as they directly reflect cerebral cortex activity. However, due...

Full description

Saved in:
Bibliographic Details
Main Authors: Lifeng You, Tianyu Zhong, Erheng He, Xuejie Liu, Qinghua Zhong
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-04-01
Series:Frontiers in Human Neuroscience
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fnhum.2025.1445763/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850145637936398336
author Lifeng You
Tianyu Zhong
Erheng He
Xuejie Liu
Qinghua Zhong
author_facet Lifeng You
Tianyu Zhong
Erheng He
Xuejie Liu
Qinghua Zhong
author_sort Lifeng You
collection DOAJ
description IntroductionEmotion recognition is crucial in facilitating human-computer emotional interaction. To enhance the credibility and realism of emotion recognition, researchers have turned to physiological signals, particularly EEG signals, as they directly reflect cerebral cortex activity. However, due to inter-subject variability and non-smoothness of EEG signals, the generalization performance of models across subjects remains a challenge.MethodsIn this study, we proposed a novel approach that combines time-frequency analysis and brain functional networks to construct dynamic brain functional networks using sliding time windows. This integration of time, frequency, and spatial domains helps to effectively capture features, reducing inter-individual differences, and improving model generalization performance. To construct brain functional networks, we employed mutual information to quantify the correlation between EEG channels and set appropriate thresholds. We then extracted three network attribute features—global efficiency, local efficiency, and local clustering coefficients—to achieve emotion classification based on dynamic brain network features.ResultsThe proposed method is evaluated on the DEAP dataset through subject-dependent (trial-independent), subject-independent, and subject- and trial-independent experiments along both valence and arousal dimensions. The results demonstrate that our dynamic brain functional network outperforms the static brain functional network in all three experimental cases. High classification accuracies of 90.89% and 91.17% in the valence and arousal dimensions, respectively, were achieved on the subject-independent experiments based on the dynamic brain function, leading to significant advancements in EEG-based emotion recognition. In addition, experiments with each brain region yielded that the left and right temporal lobes focused on processing individual private emotional information, whereas the remaining brain regions paid attention to processing basic emotional information.
format Article
id doaj-art-32bf5e42c3e043f2a6d1e1f4671fb424
institution OA Journals
issn 1662-5161
language English
publishDate 2025-04-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Human Neuroscience
spelling doaj-art-32bf5e42c3e043f2a6d1e1f4671fb4242025-08-20T02:28:02ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612025-04-011910.3389/fnhum.2025.14457631445763Cross-subject affective analysis based on dynamic brain functional networksLifeng You0Tianyu Zhong1Erheng He2Xuejie Liu3Qinghua Zhong4School of Physics, South China Normal University, Guangzhou, ChinaSchool of Social Sciences, Nanyang Technological University, Singapore, SingaporeSchool of Physics, South China Normal University, Guangzhou, ChinaSchool of Electronic Science and Engineering (School of Microelectronics), South China Normal University, Foshan, ChinaSchool of Electronic Science and Engineering (School of Microelectronics), South China Normal University, Foshan, ChinaIntroductionEmotion recognition is crucial in facilitating human-computer emotional interaction. To enhance the credibility and realism of emotion recognition, researchers have turned to physiological signals, particularly EEG signals, as they directly reflect cerebral cortex activity. However, due to inter-subject variability and non-smoothness of EEG signals, the generalization performance of models across subjects remains a challenge.MethodsIn this study, we proposed a novel approach that combines time-frequency analysis and brain functional networks to construct dynamic brain functional networks using sliding time windows. This integration of time, frequency, and spatial domains helps to effectively capture features, reducing inter-individual differences, and improving model generalization performance. To construct brain functional networks, we employed mutual information to quantify the correlation between EEG channels and set appropriate thresholds. We then extracted three network attribute features—global efficiency, local efficiency, and local clustering coefficients—to achieve emotion classification based on dynamic brain network features.ResultsThe proposed method is evaluated on the DEAP dataset through subject-dependent (trial-independent), subject-independent, and subject- and trial-independent experiments along both valence and arousal dimensions. The results demonstrate that our dynamic brain functional network outperforms the static brain functional network in all three experimental cases. High classification accuracies of 90.89% and 91.17% in the valence and arousal dimensions, respectively, were achieved on the subject-independent experiments based on the dynamic brain function, leading to significant advancements in EEG-based emotion recognition. In addition, experiments with each brain region yielded that the left and right temporal lobes focused on processing individual private emotional information, whereas the remaining brain regions paid attention to processing basic emotional information.https://www.frontiersin.org/articles/10.3389/fnhum.2025.1445763/fullEEGemotion recognitiondynamic brain function networksubject independencesubject and trial independence
spellingShingle Lifeng You
Tianyu Zhong
Erheng He
Xuejie Liu
Qinghua Zhong
Cross-subject affective analysis based on dynamic brain functional networks
Frontiers in Human Neuroscience
EEG
emotion recognition
dynamic brain function network
subject independence
subject and trial independence
title Cross-subject affective analysis based on dynamic brain functional networks
title_full Cross-subject affective analysis based on dynamic brain functional networks
title_fullStr Cross-subject affective analysis based on dynamic brain functional networks
title_full_unstemmed Cross-subject affective analysis based on dynamic brain functional networks
title_short Cross-subject affective analysis based on dynamic brain functional networks
title_sort cross subject affective analysis based on dynamic brain functional networks
topic EEG
emotion recognition
dynamic brain function network
subject independence
subject and trial independence
url https://www.frontiersin.org/articles/10.3389/fnhum.2025.1445763/full
work_keys_str_mv AT lifengyou crosssubjectaffectiveanalysisbasedondynamicbrainfunctionalnetworks
AT tianyuzhong crosssubjectaffectiveanalysisbasedondynamicbrainfunctionalnetworks
AT erhenghe crosssubjectaffectiveanalysisbasedondynamicbrainfunctionalnetworks
AT xuejieliu crosssubjectaffectiveanalysisbasedondynamicbrainfunctionalnetworks
AT qinghuazhong crosssubjectaffectiveanalysisbasedondynamicbrainfunctionalnetworks