EEG-Based Multi-Level Mental State Classification Using Partial Directed Coherence and Graph Convolutional Networks: Impact of Binaural Beats on Stress Mitigation

This study addresses limitations in EEG-based stress detection research by developing a novel approach to differentiate multiple mental states in different stress baseline population samples. Utilizing EEG signals, graph convolutional neural networks (GCNs), and binaural beats stimulation (BBs), the...

Full description

Saved in:
Bibliographic Details
Main Author: Badr, Yara (author)
Other Authors: Yahya, Fares (author), Khan, Malik Nasir Afzal (author), Ali, Nour Faris (author), Tariq, Usman (author), Almughairbi, Fadwa (author), Babiloni, Fabio (author), Al-Nashash, Hasan (author)
Format: article
Published: 2025
Subjects:
Online Access:https://hdl.handle.net/11073/26084
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513440805027840
author Badr, Yara
author2 Yahya, Fares
Khan, Malik Nasir Afzal
Ali, Nour Faris
Tariq, Usman
Almughairbi, Fadwa
Babiloni, Fabio
Al-Nashash, Hasan
author2_role author
author
author
author
author
author
author
author_facet Badr, Yara
Yahya, Fares
Khan, Malik Nasir Afzal
Ali, Nour Faris
Tariq, Usman
Almughairbi, Fadwa
Babiloni, Fabio
Al-Nashash, Hasan
author_role author
dc.creator.none.fl_str_mv Badr, Yara
Yahya, Fares
Khan, Malik Nasir Afzal
Ali, Nour Faris
Tariq, Usman
Almughairbi, Fadwa
Babiloni, Fabio
Al-Nashash, Hasan
dc.date.none.fl_str_mv 2025-06-02T08:18:13Z
2025-06-02T08:18:13Z
2025-04
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Y. Badr et al., "EEG-Based Multi-Level Mental State Classification Using Partial Directed Coherence and Graph Convolutional Networks: Impact of Binaural Beats on Stress Mitigation," in IEEE Access, vol. 13, pp. 61284-61298, 2025, doi: 10.1109/ACCESS.2025.3553932.
2169-3536
https://hdl.handle.net/11073/26084
10.1109/ACCESS.2025.3553932.
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv IEEE
dc.relation.none.fl_str_mv https://doi.org/10.1109/ACCESS.2025.3553932
dc.subject.none.fl_str_mv Mental stress
EEG
Deep learning
GCN
PDC
Binaural beats stimulation
dc.title.none.fl_str_mv EEG-Based Multi-Level Mental State Classification Using Partial Directed Coherence and Graph Convolutional Networks: Impact of Binaural Beats on Stress Mitigation
dc.type.none.fl_str_mv Peer-Reviewed
Published version
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description This study addresses limitations in EEG-based stress detection research by developing a novel approach to differentiate multiple mental states in different stress baseline population samples. Utilizing EEG signals, graph convolutional neural networks (GCNs), and binaural beats stimulation (BBs), the research investigates stress detection and reduction in two population sample groups with distinct baselines (group 1: low daily baseline, and group 2: stressed daily baseline). The experiment comprises four phases: rest state, control alertness, stress induction, and stress mitigation. Mental states were assessed using behavioral data: reaction time to stimuli (RT) and target detection accuracy, subjective reports: Perceived Stress Scale scores (PSS-10), biochemical indicators: salivary cortisol levels, and neurophysiological measure: EEG effective connectivity via Partial Directed Coherence (PDC). BBs significantly improved target detection accuracy by 31.6% and 22.8% for low and high-stress groups, respectively. PDC connectivity showed a shift to the temporal region during mitigation, indicating a return to a more balanced state. GCN classification achieved accuracies of 76.43 ± 9.01% and 76.32 ± 7.79% for each group, and 76.37 ± 8.40% for a common baseline. While 16-Hz BBs enhanced focusing abilities they did not significantly reduce subjective stress scores. This study highlights the complex relationship between cognitive performance, perceived stress, and neurophysiological measures, emphasizing the need for multifaceted stress research and management approaches.
format article
id aus_94446c8f6586e52185dc74bee453164a
identifier_str_mv Y. Badr et al., "EEG-Based Multi-Level Mental State Classification Using Partial Directed Coherence and Graph Convolutional Networks: Impact of Binaural Beats on Stress Mitigation," in IEEE Access, vol. 13, pp. 61284-61298, 2025, doi: 10.1109/ACCESS.2025.3553932.
2169-3536
10.1109/ACCESS.2025.3553932.
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/26084
publishDate 2025
publisher.none.fl_str_mv IEEE
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling EEG-Based Multi-Level Mental State Classification Using Partial Directed Coherence and Graph Convolutional Networks: Impact of Binaural Beats on Stress MitigationBadr, YaraYahya, FaresKhan, Malik Nasir AfzalAli, Nour FarisTariq, UsmanAlmughairbi, FadwaBabiloni, FabioAl-Nashash, HasanMental stressEEGDeep learningGCNPDCBinaural beats stimulationThis study addresses limitations in EEG-based stress detection research by developing a novel approach to differentiate multiple mental states in different stress baseline population samples. Utilizing EEG signals, graph convolutional neural networks (GCNs), and binaural beats stimulation (BBs), the research investigates stress detection and reduction in two population sample groups with distinct baselines (group 1: low daily baseline, and group 2: stressed daily baseline). The experiment comprises four phases: rest state, control alertness, stress induction, and stress mitigation. Mental states were assessed using behavioral data: reaction time to stimuli (RT) and target detection accuracy, subjective reports: Perceived Stress Scale scores (PSS-10), biochemical indicators: salivary cortisol levels, and neurophysiological measure: EEG effective connectivity via Partial Directed Coherence (PDC). BBs significantly improved target detection accuracy by 31.6% and 22.8% for low and high-stress groups, respectively. PDC connectivity showed a shift to the temporal region during mitigation, indicating a return to a more balanced state. GCN classification achieved accuracies of 76.43 ± 9.01% and 76.32 ± 7.79% for each group, and 76.37 ± 8.40% for a common baseline. While 16-Hz BBs enhanced focusing abilities they did not significantly reduce subjective stress scores. This study highlights the complex relationship between cognitive performance, perceived stress, and neurophysiological measures, emphasizing the need for multifaceted stress research and management approaches.American University of SharjahFourth Forum for Women in ResearchCollege of EngineeringDepartment of Electrical EngineeringIEEE2025-06-02T08:18:13Z2025-06-02T08:18:13Z2025-04Peer-ReviewedPublished versioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfY. Badr et al., "EEG-Based Multi-Level Mental State Classification Using Partial Directed Coherence and Graph Convolutional Networks: Impact of Binaural Beats on Stress Mitigation," in IEEE Access, vol. 13, pp. 61284-61298, 2025, doi: 10.1109/ACCESS.2025.3553932.2169-3536https://hdl.handle.net/11073/2608410.1109/ACCESS.2025.3553932.en_UShttps://doi.org/10.1109/ACCESS.2025.3553932oai:repository.aus.edu:11073/260842025-06-02T11:53:14Z
spellingShingle EEG-Based Multi-Level Mental State Classification Using Partial Directed Coherence and Graph Convolutional Networks: Impact of Binaural Beats on Stress Mitigation
Badr, Yara
Mental stress
EEG
Deep learning
GCN
PDC
Binaural beats stimulation
status_str publishedVersion
title EEG-Based Multi-Level Mental State Classification Using Partial Directed Coherence and Graph Convolutional Networks: Impact of Binaural Beats on Stress Mitigation
title_full EEG-Based Multi-Level Mental State Classification Using Partial Directed Coherence and Graph Convolutional Networks: Impact of Binaural Beats on Stress Mitigation
title_fullStr EEG-Based Multi-Level Mental State Classification Using Partial Directed Coherence and Graph Convolutional Networks: Impact of Binaural Beats on Stress Mitigation
title_full_unstemmed EEG-Based Multi-Level Mental State Classification Using Partial Directed Coherence and Graph Convolutional Networks: Impact of Binaural Beats on Stress Mitigation
title_short EEG-Based Multi-Level Mental State Classification Using Partial Directed Coherence and Graph Convolutional Networks: Impact of Binaural Beats on Stress Mitigation
title_sort EEG-Based Multi-Level Mental State Classification Using Partial Directed Coherence and Graph Convolutional Networks: Impact of Binaural Beats on Stress Mitigation
topic Mental stress
EEG
Deep learning
GCN
PDC
Binaural beats stimulation
url https://hdl.handle.net/11073/26084