《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (11): 3354-3363.DOI: 10.11772/j.issn.1001-9081.2023111593

• 人工智能 • 上一篇    下一篇

运动想象脑电图的空域特征迁移核学习方法

杨思琪1,2, 罗天健1,2(), 严宣辉1,2, 杨光局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
  • 收稿日期:2023-11-20 修回日期:2024-03-19 接受日期:2024-03-21 发布日期:2024-03-22 出版日期:2024-11-10
  • 通讯作者: 罗天健
  • 作者简介:杨思琪(2000—),女,湖南衡阳人,硕士研究生,CCF会员,主要研究方向:脑机接口、模式识别
    严宣辉(1968—),男,福建福州人,教授,博士,主要研究方向:模式识别
    杨光局(1999—),男,福建三明人,硕士研究生,CCF会员,主要研究方向:模式识别。
  • 基金资助:
    国家自然科学基金资助项目(62106049);福建省自然科学基金资助项目(2022J01655)

Transfer kernel learning method based on spatial features for motor imagery EEG

Siqi YANG1,2, Tianjian LUO1,2(), Xuanhui YAN1,2, Guangju YANG1,2   

  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:2023-11-20 Revised:2024-03-19 Accepted:2024-03-21 Online:2024-03-22 Published:2024-11-10
  • Contact: Tianjian LUO
  • About author:YANG Siqi, born in 2000, M. S. candidate. Her research interests include brain computer interface, pattern recognition.
    YAN Xuanhui, born in 1968, Ph. D., professor. His research interests include pattern recognition.
    YANG Guangju, born in 1999, M. S. candidate. His research interests include pattern recognition.
  • Supported by:
    National Natural Science Foundation of China(62106049);Natural Science Foundation of Fujian Province(2022J01655)

摘要:

运动想象脑电(MI-EEG)信号在构建临床辅助康复的无创脑机接口(BCI)中获得了广泛关注。受限于不同被试者的MI-EEG信号样本分布存在差异,跨被试MI-EEG信号的特征学习成为研究重点。然而,现有的相关方法存在域不变特征表达能力弱、时间复杂度较高等问题,无法直接应用于在线BCI。为解决该问题,提出黎曼切空间特征迁移核学习(TKRTS)方法,并基于此构建了高效的跨被试MI-EEG信号分类算法。TKRTS方法首先将MI-EEG信号协方差矩阵投影至黎曼空间,并在黎曼空间上对齐不同被试者的协方差矩阵,同时提取黎曼切空间(RTS)特征;随后,学习RTS特征集上的域不变核矩阵,从而获得完备的跨被试MI-EEG特征表达,并通过该矩阵训练核支持向量机(KSVM)进行分类。为验证TKRTS方法的可行性与有效性,在3个公开数据集上分别进行多源域-单目标域以及单源域-单目标域的实验,平均分类准确率分别提升了0.81个百分点和0.13个百分点。实验结果表明,与主流方法对比,TKRTS方法提升了平均分类准确率并保持相似的时间复杂度。此外,消融实验结果验证了TKRTS方法对跨被试特征表达的完备性和参数不敏感性,适合构建在线脑接机口。

关键词: 运动想象, 脑电信号, 跨被试, 黎曼切空间特征, 迁移核学习

Abstract:

Motor Imagery ElectroEncephaloGram (MI-EEG) signal has gained widespread attention in the construction of non-invasive Brain Computer Interfaces (BCIs) for clinical assisted rehabilitation. Limited by the differences in the distribution of MI-EEG signal samples from different subjects, cross-subject MI-EEG signal feature learning has become the focus of research. However, the existing related methods have problems such as weak domain-invariant feature expression capabilities and high time complexity, and cannot be directly applied to online BCIs. To address this issue, an efficient cross-subject MI-EEG signal classification algorithm, Transfer Kernel Riemannian Tangent Space (TKRTS), was proposed. Firstly, the MI-EEG signal covariance matrices were projected into the Riemannian space and the covariance matrices of different subjects were aligned in Riemannian space while extracting Riemannian Tangent Space (RTS) features. Subsequently, the domain-invariant kernel matrix on the tangent space feature set was learnt, thereby achieving a complete representation of cross-subject MI?EEG signal features. This matrix was then used to train a Kernel Support Vector Machine (KSVM) for classification. To validate the feasibility and effectiveness of TKRTS method, multi-source domain to single-target domain and single-source domain to single-target domain experiments were conducted on three public datasets, and the average classification accuracy is increased by 0.81 and 0.13 percentage points respectively. Experimental results demonstrate that compared to state-of-the-art methods, TKRTS method improves the average classification accuracy while maintaining similar time complexity. Furthermore, ablation experimental results confirm the completeness and parameter insensitivity of TKRTS method in cross-subject feature expression, making this method suitable for constructing online BCIs.

Key words: motor imagery, ElectroEncephaloGram (EEG) signal, cross-subject, Riemannian Tangent Space (RTS) feature, Transfer Kernel Learning (TKL)

中图分类号: