基于黎曼空间滤波与域适应的跨时间运动想象-脑电解码研究  

Cross-session motor imagery-electroencephalography decoding with Riemannian spatial filtering and domain adaptation

作　　者：潘林聪 孙新维 王坤 曹愉培 许敏鹏 明东 PAN Lincong;SUN Xinwei;WANG Kun;CAO Yupei;XU Minpeng;MING Dong(Academy of Medical Engineering and Translational Medicine,Tianjin University,Tianjin 300072,P.R.China;School of Precision Instruments and Opto-Electronic Engineering,Tianjin University,Tianjin 300072,P.R.China;Haihe Laboratory of Brain-computer Interaction and Human-machine Integration,Tianjin 300392,P.R.China)

机构地区：[1]天津大学医学工程与转化医学研究院,天津300072 [2]天津大学精密仪器与光电子工程学院,天津300072 [3]脑机交互与人机共融海河实验室,天津300392

出　　处：《生物医学工程学杂志》2025年第2期272-279,共8页Journal of Biomedical Engineering

基　　金：国家自然科学基金项目(62122059,62206198)。

摘　　要：运动想象(MI)是一种无需实际运动即可通过脑电图(EEG)识别的心理过程,它在脑-机接口(BCI)技术领域具有重要的研究价值和应用前景。然而,MI-EEG信号的非平稳性和低信噪比使得其分类成为一项挑战。本研究提出了一种基于黎曼空间滤波与域适应(RSFDA)的方法,旨在提高MI-BCI跨时间分类任务的准确性与效率。该方法通过多模块协同的方式,有效解决了源域与目标域数据分布不一致的问题,提升了跨时间MI-EEG分类任务的泛化能力。本文在三个公开数据集上对比了RSFDA与八种现有竞争方法的分类准确率和训练时间成本。结果显示,RSFDA的平均分类准确率为79.37%,对比分类效果最好的深度学习方法 TensorCSPNet的76.46%提高了2.91%(P <0.01)。此外,RSFDA还具有较低的计算成本,平均训练时间约为3 min,对比Tensor-CSPNet的25 min缩短了22 min。因此,RSFDA方法在跨时间的MI-EEG分类任务中表现出色,兼具准确性和高效性,但它在复杂迁移场景中的表现仍需进一步研究和验证。Motor imagery(MI) is a mental process that can be recognized by electroencephalography(EEG) without actual movement. It has significant research value and application potential in the field of brain-computer interface(BCI) technology. To address the challenges posed by the non-stationary nature and low signal-to-noise ratio of MI-EEG signals, this study proposed a Riemannian spatial filtering and domain adaptation(RSFDA) method for improving the accuracy and efficiency of cross-session MI-BCI classification tasks. The approach addressed the issue of inconsistent data distribution between source and target domains through a multi-module collaborative framework, which enhanced the generalization capability of cross-session MI-EEG classification models. Comparative experiments were conducted on three public datasets to evaluate RSFDA against eight existing methods in terms of classification accuracy and computational efficiency. The experimental results demonstrated that RSFDA achieved an average classification accuracy of 79.37%, outperforming the state-of-the-art deep learning method Tensor-CSPNet(76.46%) by 2.91%(P <0.01). Furthermore, the proposed method showed significantly lower computational costs, requiring only approximately 3minutes of average training time compared to Tensor-CSPNet's 25 minutes, representing a reduction of 22 minutes. These findings indicate that the RSFDA method demonstrates superior performance in cross-session MI-EEG classification tasks by effectively balancing accuracy and efficiency. However, its applicability in complex transfer learning scenarios remains to be further investigated.

关 键 词：脑-机接口 脑电信号 运动想象 机器学习 跨时间 

分 类 号：R318[医药卫生—生物医学工程]