Hybrid Network Using Dynamic Graph Convolution and Temporal Self-Attention for EEG-Based Emotion Recognition

被引:4
|
作者
Cheng, Cheng [1 ]
Yu, Zikang [1 ]
Zhang, Yong [2 ]
Feng, Lin [1 ]
机构
[1] Dalian Univ Technol, Dept Comp Sci & Technol, Dalian 116024, Peoples R China
[2] Huzhou Univ, Dept Informat Engn, Huzhou 313000, Peoples R China
基金
中国国家自然科学基金;
关键词
Dynamic graph convolution; electroencephalogram (EEG); emotion recognition; hierarchical cross-attention fusion (H-CAF); temporal self-attention representation (TSAR);
D O I
10.1109/TNNLS.2023.3319315
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The electroencephalogram (EEG) signal has become a highly effective decoding target for emotion recognition and has garnered significant attention from researchers. Its spatial topological and time-dependent characteristics make it crucial to explore both spatial information and temporal information for accurate emotion recognition. However, existing studies often focus on either spatial or temporal aspects of EEG signals, neglecting the joint consideration of both perspectives. To this end, this article proposes a hybrid network consisting of a dynamic graph convolution (DGC) module and temporal self-attention representation (TSAR) module, which concurrently incorporates the representative knowledge of spatial topology and temporal context into the EEG emotion recognition task. Specifically, the DGC module is designed to capture the spatial functional relationships within the brain by dynamically updating the adjacency matrix during the model training process. Simultaneously, the TSAR module is introduced to emphasize more valuable time segments and extract global temporal features from EEG signals. To fully exploit the interactivity between spatial and temporal information, the hierarchical cross-attention fusion (H-CAF) module is incorporated to fuse the complementary information from spatial and temporal features. Extensive experimental results on the DEAP, SEED, and SEED-IV datasets demonstrate that the proposed method outperforms other state-of-the-art methods.
引用
收藏
页码:1 / 11
页数:11
相关论文
共 50 条
  • [1] Hybrid Network Using Dynamic Graph Convolution and Temporal Self-Attention for EEG-Based Emotion Recognition
    Dalian University of Technology, Department of Computer Science and Technology, Dalian
    116024, China
    不详
    313000, China
    [J]. IEEE Trans. Neural Networks Learn. Sys, 12 (18565-18575):
  • [2] Multiscale Temporal Self-Attention and Dynamical Graph Convolution Hybrid Network for EEG-Based Stereogram Recognition
    Shen, Lili
    Sun, Mingyang
    Li, Qunxia
    Li, Beichen
    Pan, Zhaoqing
    Lei, Jianjun
    [J]. IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2022, 30 : 1191 - 1202
  • [3] EEG-Based Emotion Recognition With Emotion Localization via Hierarchical Self-Attention
    Zhang, Yuzhe
    Liu, Huan
    Zhang, Dalin
    Chen, Xuxu
    Qin, Tao
    Zheng, Qinghua
    [J]. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2023, 14 (03) : 2458 - 2469
  • [4] EEG-Based Emotion Recognition Using Convolutional Recurrent Neural Network with Multi-Head Self-Attention
    Hu, Zhangfang
    Chen, Libujie
    Luo, Yuan
    Zhou, Jingfan
    [J]. APPLIED SCIENCES-BASEL, 2022, 12 (21):
  • [5] A Bi-Stream hybrid model with MLPBlocks and self-attention mechanism for EEG-based emotion recognition
    Li, Wei
    Tian, Ye
    Hou, Bowen
    Dong, Jianzhang
    Shao, Shitong
    Song, Aiguo
    [J]. BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2023, 86
  • [6] BiSMSM: A Hybrid MLP-Based Model of Global Self-Attention Processes for EEG-Based Emotion Recognition
    Li, Wei
    Tian, Ye
    Hou, Bowen
    Dong, Jianzhang
    Shao, Shitong
    [J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2022, PT I, 2022, 13529 : 37 - 48
  • [7] Attention-Based Temporal Graph Representation Learning for EEG-Based Emotion Recognition
    Li, Chao
    Wang, Feng
    Zhao, Ziping
    Wang, Haishuai
    Schuller, Björn W.
    [J]. IEEE Journal of Biomedical and Health Informatics, 2024, 28 (10) : 5755 - 5767
  • [8] STGATE: Spatial-temporal graph attention network with a transformer encoder for EEG-based emotion recognition
    Li, Jingcong
    Pan, Weijian
    Huang, Haiyun
    Pan, Jiahui
    Wang, Fei
    [J]. FRONTIERS IN HUMAN NEUROSCIENCE, 2023, 17
  • [9] EEG-fNIRS-Based Emotion Recognition Using Graph Convolution and Capsule Attention Network
    Chen, Guijun
    Liu, Yue
    Zhang, Xueying
    [J]. BRAIN SCIENCES, 2024, 14 (08)
  • [10] EEG-based emotion recognition using graph convolutional neural network with dual attention mechanism
    Chen, Wei
    Liao, Yuan
    Dai, Rui
    Dong, Yuanlin
    Huang, Liya
    [J]. FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2024, 18