Data augmentation for cross-subject EEG features using Siamese neural network

被引:4
|
作者
Fu, Rongrong [1 ]
Wang, Yaodong [1 ]
Jia, Chengcheng [2 ]
机构
[1] Yanshan Univ, Dept Elect Engn, Measurement Technol & Instrumentat Key Lab Hebei, Qinhuangdao, Hebei, Peoples R China
[2] Ryerson Univ, Dept Elect Comp & Biomed Engn, Toronto, ON, Canada
基金
中国博士后科学基金; 中国国家自然科学基金;
关键词
Complex motor recognition; Data augmentation; Siamese neural network; Similarity measurement; Transfer learning; COMMON SPATIAL-PATTERN; CLASSIFICATION; TIME; CNN;
D O I
10.1016/j.bspc.2022.103614
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Electroencephalography (EEG) motor intention recognition has been extensively used in robot control, brain rehabilitation and other health care fields. Recently, some algorithms have been proposed based on generative adversarial neural network (GAN) to enhance EEG signal, and have achieved high recognition performance. However, these methods utilize the convolutional kernel method of the GAN, while the optimal convolutional scale of CNN varies from subject to subject. This may lead to the data generated by GAN to lack authenticity and produce data that does not match the ideal situation. Particularly, the performance of data augmentation degrades when the original calibrated EEG is insufficient. To address these issues, we proposed a novel cross-subject Siamese Neural Network (SNN) approach to enhance EEG feature data. Specifically, we used our proposed SNN to construct highly similar extended EEG features of different subjects and successfully improved the performance of motor intention recognition. Then, we design an accurate boundary avoidance task to evaluate the effectiveness of the proposed method. Compared with the traditional experimental paradigm, the coding process of this experiment is more complex, which makes the results more reliable when using the SNN. The extended EEG features display significantly better performance than any other common classifiers in the case of small data size, and it demonstrates that this proposed method can effectively address these issues of existing EEG motor intention recognition methods based on data augmentation and improve the classification performance.
引用
收藏
页数:9
相关论文
共 50 条
  • [1] Cross-Subject Emotion Recognition Using Fused Entropy Features of EEG
    Zuo, Xin
    Zhang, Chi
    Hamalainen, Timo
    Gao, Hanbing
    Fu, Yu
    Cong, Fengyu
    ENTROPY, 2022, 24 (09)
  • [2] Exploring EEG Features in Cross-Subject Emotion Recognition
    Li, Xiang
    Song, Dawei
    Zhang, Peng
    Zhang, Yazhou
    Hou, Yuexian
    Hu, Bin
    FRONTIERS IN NEUROSCIENCE, 2018, 12
  • [3] Fusion Convolutional Neural Network for Cross-Subject EEG Motor Imagery Classification
    Roots, Karel
    Muhammad, Yar
    Muhammad, Naveed
    COMPUTERS, 2020, 9 (03) : 1 - 9
  • [4] Cross-Subject EEG Emotion Recognition With Self-Organized Graph Neural Network
    Li, Jingcong
    Li, Shuqi
    Pan, Jiahui
    Wang, Fei
    FRONTIERS IN NEUROSCIENCE, 2021, 15
  • [5] Cross-Subject emotion recognition from EEG using Convolutional Neural Networks
    Zhong, Xiaolong
    Yin, Zhong
    Zhang, Jianhua
    PROCEEDINGS OF THE 39TH CHINESE CONTROL CONFERENCE, 2020, : 7516 - 7521
  • [6] Cross-Subject EEG Signal Recognition Using Deep Domain Adaptation Network
    Hang, Wenlong
    Feng, Wei
    Du, Ruoyu
    Liang, Shuang
    Chen, Yan
    Wang, Qiong
    Liu, Xuejun
    IEEE ACCESS, 2019, 7 : 128273 - 128282
  • [7] Single-channel EEG sleep staging based on data augmentation and cross-subject discrepancy alleviation
    He, Zhengling
    Du, Lidong
    Wang, Peng
    Xia, Pan
    Liu, Zhe
    Song, Yuanlin
    Chen, Xianxiang
    Fang, Zhen
    COMPUTERS IN BIOLOGY AND MEDICINE, 2022, 149
  • [8] EEG-Based Cross-Subject Driver Drowsiness Recognition With an Interpretable Convolutional Neural Network
    Cui, Jian
    Lan, Zirui
    Sourina, Olga
    Muller-Wittig, Wolfgang
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (10) : 7921 - 7933
  • [9] Investigating the Use of Pretrained Convolutional Neural Network on Cross-Subject and Cross-Dataset EEG Emotion Recognition
    Cimtay, Yucel
    Ekmekcioglu, Erhan
    SENSORS, 2020, 20 (07)
  • [10] Cross-subject network investigation of the EEG microstructure: A sleep spindles study
    Sakellariou, Dimitris F.
    Koutroumanidis, Michalis
    Richardson, Mark P.
    Kostopoulos, George K.
    JOURNAL OF NEUROSCIENCE METHODS, 2019, 312 : 16 - 26