Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (2): 645-653.DOI: 10.11772/j.issn.1001-9081.2023030286

• Frontier and comprehensive applications • Previous Articles    

Dynamic multi-domain adversarial learning method for cross-subject motor imagery EEG signals

Xuan CAO1,2, Tianjian LUO1,2()   

  1. 1.College of Computer and Cyber Security,Fujian Normal University,Fuzhou Fujian 350117,China
    2.Digital Fujian Internet?of?Thing Laboratory of Environmental Monitoring (Fujian Normal University),Fuzhou Fujian 350117,China
  • Received:2023-03-20 Revised:2023-05-06 Accepted:2023-05-10 Online:2023-05-26 Published:2024-02-10
  • Contact: Tianjian LUO
  • About author:CAO Xuan, born in 1998, M. S. candidate. His research interests include brain computer interface, pattern recognition, EEG signal analysis.
  • Supported by:
    National Natural Science Foundation of China(62106049);Natural Science Foundation of Fujian Province(2022J01655)


曹铉1,2, 罗天健1,2()   

  1. 1.福建师范大学 计算机与网络空间安全学院,福州 350117
    2.数字福建环境监测物联网实验室(福建师范大学),福州 350117
  • 通讯作者: 罗天健
  • 作者简介:曹铉(1998—),男,山东兖州人,硕士研究生,主要研究方向:脑机接口、模式识别、脑电信号分析;
  • 基金资助:


Decoding motor imagery EEG (ElectroEncephaloGraphy) signal is one of the crucial techniques for building Brain Computer Interface (BCI) system. Due to EEG signal’s high cost of acquisition, large inter-subject discrepancy, and characteristics of strong time variability and low signal-to-noise ratio, constructing cross-subject pattern recognition methods become the key problem of such study. To solve the existing problem, a cross-subject dynamic multi-domain adversarial learning method was proposed. Firstly, the covariance matrix alignment method was used to align the given EEG samples. Then, a global discriminator was adapted for marginal distribution of different domains, and multiple class-wise local discriminators were adapted to conditional distribution for each class. The self-adaptive adversarial factor for multi-domain discriminator was automatically learned during training iterations. Based on dynamic multi-domain adversarial learning strategy, the Dynamic Multi-Domain Adversarial Network (DMDAN) model could learn deep features with generalization ability between cross-subject domains. Experimental results on public BCI Competition IV 2A and 2B datasets show that, DMDAN model improves the ability of learning domain-invariant features, achieving 1.80 and 2.52 percentage points higher average classification accuracy on dataset 2A and dataset 2B compared with the existing adversarial learning method Deep Representation Domain Adaptation (DRDA). It can be seen that DMDAN model improves the decoding performance of cross-subject motor imagery EEG signals, and has generalization ability on different datasets.

Key words: dynamic adversarial learning, Motor Imagery (MI), EEG (ElectroEncephaloGraphy) signal, domain adaptation, covariance matrix alignment


解码运动想象脑电(EEG)信号是构造脑机接口(BCI)的关键技术之一。然而,脑电样本采集成本高、个体差异大,且信号具有时变性强、低信噪比等特点,构建跨被试模式识别方法成为了研究的关键。为此,提出一种跨被试动态多域对抗学习方法。首先采用样本协方差对齐和全局域鉴别器适应样本集边缘分布,随后采用多个类别子域鉴别器适应样本集条件分布,并自适应学习多域鉴别器的对抗系数。基于动态多域对抗学习策略,所提出的动态多域对抗网络(DMDAN)模型可学习到被试域间有泛化能力的深度特征。在BCI Competition IV 2A和2B公开数据集上的实验结果表明,DMDAN模型提高了跨被试域不变特征的学习能力,与现有对抗学习方法DRDA(Deep Representation Domain Adaptation)相比,在数据集2A和数据集2B上的平均分类准确率分别提高了1.80和2.52个百分点。可见,所提出的DMDAN模型提升了跨被试运动想象脑电信号解码性能,在不同数据集上具有不错的泛化性。

关键词: 动态对抗学习, 运动想象, 脑电信号, 域适应, 协方差矩阵对齐

CLC Number: