An Improved Dual Stream DGCNN Method for Fine-Grained Positive Emotion Classification

Shuming Hu; Zhiwen Yu; En Xu; Yao Wang; Ying Zhang; Bin Guo

doi:10.1109/BESC64747.2024.10780604

An Improved Dual Stream DGCNN Method for Fine-Grained Positive Emotion Classification

Shuming Hu, Zhiwen Yu, En Xu, Yao Wang, Ying Zhang, Bin Guo

Department of Physics

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

Abstract

Recent advances in EEG-based emotion computation have garnered significant interest from the fields of neuroscience and computer science. Despite this, the bulk of EEG-based emotion classification research has concentrated on the dimensions of arousal and valence, with scant attention to the classification of positive emotions as experienced in daily life. Addressing this gap, our study focuses on the classification of four specific positive emotions using the open-source FACED dataset. We processed EEG data by segmenting it, extracting features, and then designing and training the DualStreamDGCNN deep learning model, which achieved the best accuracy of 60.88%. Furthermore, we visualized the adjacency matrices of the four emotions from our model, offering insights from a neuroscientific perspective. This research is pivotal for advancing our understanding of the types and dynamics of positive emotions in practical applications, such as enhancing educational environments and boosting employee efficiency.

Original language	English
Title of host publication	Proceedings of the 2024 IEEE International Conference on Behavioural and Social Computing, BESC 2024
Publisher	IEEE
Pages	1-6
Number of pages	6
ISBN (Electronic)	9798331531904
DOIs	https://doi.org/10.1109/BESC64747.2024.10780604
Publication status	Published - Aug 2024
Event	11th IEEE International Conference on Behavioural and Social Computing, BESC 2024 - Harbin, China Duration: 16 Aug 2024 → 18 Aug 2024 https://ieeexplore.ieee.org/xpl/conhome/10779601/proceeding (Conference Proceedings)

Publication series

Name	Proceedings of the IEEE International Conference on Behavioural and Social Computing, BESC

Conference

Conference	11th IEEE International Conference on Behavioural and Social Computing, BESC 2024
Country/Territory	China
City	Harbin
Period	16/08/24 → 18/08/24
Internet address	https://ieeexplore.ieee.org/xpl/conhome/10779601/proceeding (Conference Proceedings)

User-Defined Keywords

Electroencephalogram (EEG)
Positive Emotion Classification
Graph Neural Network (GNN)
Deep Learning

Access to Document

10.1109/BESC64747.2024.10780604

Cite this

Hu, S., Yu, Z., Xu, E., Wang, Y., Zhang, Y., & Guo, B. (2024). An Improved Dual Stream DGCNN Method for Fine-Grained Positive Emotion Classification. In Proceedings of the 2024 IEEE International Conference on Behavioural and Social Computing, BESC 2024 (pp. 1-6). (Proceedings of the IEEE International Conference on Behavioural and Social Computing, BESC). IEEE. https://doi.org/10.1109/BESC64747.2024.10780604

@inproceedings{8700096f73fb41bcbd6ce8d796d30a22,

title = "An Improved Dual Stream DGCNN Method for Fine-Grained Positive Emotion Classification",

abstract = "Recent advances in EEG-based emotion computation have garnered significant interest from the fields of neuroscience and computer science. Despite this, the bulk of EEG-based emotion classification research has concentrated on the dimensions of arousal and valence, with scant attention to the classification of positive emotions as experienced in daily life. Addressing this gap, our study focuses on the classification of four specific positive emotions using the open-source FACED dataset. We processed EEG data by segmenting it, extracting features, and then designing and training the DualStreamDGCNN deep learning model, which achieved the best accuracy of 60.88%. Furthermore, we visualized the adjacency matrices of the four emotions from our model, offering insights from a neuroscientific perspective. This research is pivotal for advancing our understanding of the types and dynamics of positive emotions in practical applications, such as enhancing educational environments and boosting employee efficiency.",

keywords = "Electroencephalogram (EEG), Positive Emotion Classification, Graph Neural Network (GNN), Deep Learning",

author = "Shuming Hu and Zhiwen Yu and En Xu and Yao Wang and Ying Zhang and Bin Guo",

note = "The authors would like to thank the editor and reviewers for their valuable comments, which helped to improve this article. This work is supported by the National Natural Science Foundation of China No. 61960206008 and No. 62272390. Publisher Copyright: {\textcopyright}2024 by the Institute of Electrical and Electronics Engineers, Inc. All rights reserved.; 11th IEEE International Conference on Behavioural and Social Computing, BESC 2024 ; Conference date: 16-08-2024 Through 18-08-2024",

year = "2024",

month = aug,

doi = "10.1109/BESC64747.2024.10780604",

language = "English",

series = "Proceedings of the IEEE International Conference on Behavioural and Social Computing, BESC",

publisher = "IEEE",

pages = "1--6",

booktitle = "Proceedings of the 2024 IEEE International Conference on Behavioural and Social Computing, BESC 2024",

address = "United States",

url = "https://ieeexplore.ieee.org/xpl/conhome/10779601/proceeding",

}

Hu, S, Yu, Z, Xu, E, Wang, Y, Zhang, Y & Guo, B 2024, An Improved Dual Stream DGCNN Method for Fine-Grained Positive Emotion Classification. in Proceedings of the 2024 IEEE International Conference on Behavioural and Social Computing, BESC 2024. Proceedings of the IEEE International Conference on Behavioural and Social Computing, BESC, IEEE, pp. 1-6, 11th IEEE International Conference on Behavioural and Social Computing, BESC 2024, Harbin, China, 16/08/24. https://doi.org/10.1109/BESC64747.2024.10780604

An Improved Dual Stream DGCNN Method for Fine-Grained Positive Emotion Classification. / Hu, Shuming; Yu, Zhiwen; Xu, En et al.
Proceedings of the 2024 IEEE International Conference on Behavioural and Social Computing, BESC 2024. IEEE, 2024. p. 1-6 (Proceedings of the IEEE International Conference on Behavioural and Social Computing, BESC).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - An Improved Dual Stream DGCNN Method for Fine-Grained Positive Emotion Classification

AU - Hu, Shuming

AU - Yu, Zhiwen

AU - Xu, En

AU - Wang, Yao

AU - Zhang, Ying

AU - Guo, Bin

N1 - The authors would like to thank the editor and reviewers for their valuable comments, which helped to improve this article. This work is supported by the National Natural Science Foundation of China No. 61960206008 and No. 62272390. Publisher Copyright: ©2024 by the Institute of Electrical and Electronics Engineers, Inc. All rights reserved.

PY - 2024/8

Y1 - 2024/8

N2 - Recent advances in EEG-based emotion computation have garnered significant interest from the fields of neuroscience and computer science. Despite this, the bulk of EEG-based emotion classification research has concentrated on the dimensions of arousal and valence, with scant attention to the classification of positive emotions as experienced in daily life. Addressing this gap, our study focuses on the classification of four specific positive emotions using the open-source FACED dataset. We processed EEG data by segmenting it, extracting features, and then designing and training the DualStreamDGCNN deep learning model, which achieved the best accuracy of 60.88%. Furthermore, we visualized the adjacency matrices of the four emotions from our model, offering insights from a neuroscientific perspective. This research is pivotal for advancing our understanding of the types and dynamics of positive emotions in practical applications, such as enhancing educational environments and boosting employee efficiency.

AB - Recent advances in EEG-based emotion computation have garnered significant interest from the fields of neuroscience and computer science. Despite this, the bulk of EEG-based emotion classification research has concentrated on the dimensions of arousal and valence, with scant attention to the classification of positive emotions as experienced in daily life. Addressing this gap, our study focuses on the classification of four specific positive emotions using the open-source FACED dataset. We processed EEG data by segmenting it, extracting features, and then designing and training the DualStreamDGCNN deep learning model, which achieved the best accuracy of 60.88%. Furthermore, we visualized the adjacency matrices of the four emotions from our model, offering insights from a neuroscientific perspective. This research is pivotal for advancing our understanding of the types and dynamics of positive emotions in practical applications, such as enhancing educational environments and boosting employee efficiency.

KW - Electroencephalogram (EEG)

KW - Positive Emotion Classification

KW - Graph Neural Network (GNN)

KW - Deep Learning

UR - http://www.scopus.com/inward/record.url?scp=85215506894&partnerID=8YFLogxK

U2 - 10.1109/BESC64747.2024.10780604

DO - 10.1109/BESC64747.2024.10780604

M3 - Conference proceeding

AN - SCOPUS:85215506894

T3 - Proceedings of the IEEE International Conference on Behavioural and Social Computing, BESC

SP - 1

EP - 6

BT - Proceedings of the 2024 IEEE International Conference on Behavioural and Social Computing, BESC 2024

PB - IEEE

T2 - 11th IEEE International Conference on Behavioural and Social Computing, BESC 2024

Y2 - 16 August 2024 through 18 August 2024

ER -

Hu S, Yu Z, Xu E, Wang Y, Zhang Y, Guo B. An Improved Dual Stream DGCNN Method for Fine-Grained Positive Emotion Classification. In Proceedings of the 2024 IEEE International Conference on Behavioural and Social Computing, BESC 2024. IEEE. 2024. p. 1-6. (Proceedings of the IEEE International Conference on Behavioural and Social Computing, BESC). doi: 10.1109/BESC64747.2024.10780604

An Improved Dual Stream DGCNN Method for Fine-Grained Positive Emotion Classification

Abstract

Publication series

Conference

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this