Nuclear Norm Regularized Deep Neural Network for EEG-Based Emotion Recognition

被引:2
|
作者
Liang, Shuang [1 ,2 ]
Yin, Mingbo [3 ]
Huang, Yecheng [3 ]
Dai, Xiubin [1 ]
Wang, Qiong [4 ]
机构
[1] Nanjing Univ Posts & Telecommun, Smart Hlth Big Data Anal & Locat Serv Engn Lab Jia, Nanjing, Peoples R China
[2] Nanjing Univ, State Key Lab Novel Software Technol, Nanjing, Peoples R China
[3] Nanjing Tech Univ, Sch Comp Sci & Technol, Nanjing, Peoples R China
[4] Chinese Acad Sci, Shenzhen Inst Adv Technol, Guangdong Prov Key Lab Comp Vis & Virtual Real Tec, Shenzhen, Peoples R China
来源
FRONTIERS IN PSYCHOLOGY | 2022年 / 13卷
基金
中国国家自然科学基金;
关键词
electroencephalography (EEG); emotion recognition; affective brain-computer interface (aBCI); structural information; nuclear norm regularization; SINGLE TRIAL EEG; DECOMPOSITION;
D O I
10.3389/fpsyg.2022.924793
中图分类号
B84 [心理学];
学科分类号
04 ; 0402 ;
摘要
Electroencephalography (EEG) based emotion recognition enables machines to perceive users' affective states, which has attracted increasing attention. However, most of the current emotion recognition methods neglect the structural information among different brain regions, which can lead to the incorrect learning of high-level EEG feature representation. To mitigate possible performance degradation, we propose a novel nuclear norm regularized deep neural network framework (NRDNN) that can capture the structural information among different brain regions in EEG decoding. The proposed NRDNN first utilizes deep neural networks to learn high-level feature representations of multiple brain regions, respectively. Then, a set of weights indicating the contributions of each brain region can be automatically learned using a region-attention layer. Subsequently, the weighted feature representations of multiple brain regions are stacked into a feature matrix, and the nuclear norm regularization is adopted to learn the structural information within the feature matrix. The proposed NRDNN method can learn the high-level representations of EEG signals within multiple brain regions, and the contributions of them can be automatically adjusted by assigning a set of weights. Besides, the structural information among multiple brain regions can be captured in the learning procedure. Finally, the proposed NRDNN can perform in an efficient end-to-end manner. We conducted extensive experiments on publicly available emotion EEG dataset to evaluate the effectiveness of the proposed NRDNN. Experimental results demonstrated that the proposed NRDNN can achieve state-of-the-art performance by leveraging the structural information.
引用
收藏
页数:11
相关论文
共 50 条
  • [41] Continuous Convolutional Neural Network with 3D Input for EEG-Based Emotion Recognition
    Yang, Yilong
    Wu, Qingfeng
    Fu, Yazhen
    Chen, Xiaowei
    [J]. NEURAL INFORMATION PROCESSING (ICONIP 2018), PT VII, 2018, 11307 : 433 - 443
  • [42] A Graph Neural Network for EEG-Based Emotion Recognition With Contrastive Learning and Generative Adversarial Neural Network Data Augmentation
    Gilakjani, Sareh Soleimani
    Al Osman, Hussein
    [J]. IEEE ACCESS, 2024, 12 : 113 - 130
  • [43] EEG-based emotion recognition using 4D convolutional recurrent neural network
    Shen, Fangyao
    Dai, Guojun
    Lin, Guang
    Zhang, Jianhai
    Kong, Wanzeng
    Zeng, Hong
    [J]. COGNITIVE NEURODYNAMICS, 2020, 14 (06) : 815 - 828
  • [44] Parallel Sequence-Channel Projection Convolutional Neural Network for EEG-Based Emotion Recognition
    Shen, Lili
    Zhao, Wei
    Shi, Yanan
    Qin, Tianyi
    Liu, Bingzheng
    [J]. IEEE ACCESS, 2020, 8 : 222966 - 222976
  • [45] EEG-based Emotion Recognition Under Convolutional Neural Network with Differential Entropy Feature Maps
    Li, Yifan
    Wong, Chi Man
    Zheng, Yudian
    Wan, Feng
    Mak, Peng Un
    Pun, Sio Hang
    Vai, Mang, I
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND VIRTUAL ENVIRONMENTS FOR MEASUREMENT SYSTEMS AND APPLICATIONS (CIVEMSA 2019), 2019, : 6 - 10
  • [46] EEG-based emotion recognition using 4D convolutional recurrent neural network
    Fangyao Shen
    Guojun Dai
    Guang Lin
    Jianhai Zhang
    Wanzeng Kong
    Hong Zeng
    [J]. Cognitive Neurodynamics, 2020, 14 : 815 - 828
  • [47] 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
  • [48] EEG-based Emotion Recognition Using Discriminative Graph Regularized Extreme Learning Machine
    Zhu, Jia-Yi
    Zheng, Wei-Long
    Peng, Yong
    Duan, Ruo-Nan
    Lu, Bao-Liang
    [J]. PROCEEDINGS OF THE 2014 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2014, : 525 - 532
  • [49] Singular Learning of Deep Multilayer Perceptrons for EEG-Based Emotion Recognition
    Guo, Weili
    Li, Guangyu
    Lu, Jianfeng
    Yang, Jian
    [J]. FRONTIERS IN COMPUTER SCIENCE, 2021, 3
  • [50] Increasing the Stability of EEG-based Emotion Recognition with a Variant of Neural Processes
    Liu, Yan-Kai
    Jiang, Wei-Bang
    Lu, Bao-Liang
    [J]. 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,