基于迁移学习的手部自然动作脑电识别  

EEG recognition of natural hand movements based on transfer learning

作　　者：薛沐辉 徐宝国[1] 李浪 宋爱国[1] XUE Muhui;XU Baoguo;LI Lang;SONG Aiguo(School of Instrument Science and Engineering,Southeast University,Nanjing 210096,China)

机构地区：[1]东南大学仪器科学与工程学院,南京210096

出　　处：《南京信息工程大学学报》2025年第2期245-255,共11页Journal of Nanjing University of Information Science & Technology

基　　金：国家重点研发计划(202022YFC2405602);江苏省前沿引领技术基础研究专项(BK20192004A);江苏省自然科学基金(BK20221464)。

摘　　要：在脑机接口(BCI)领域,手部自然动作脑电识别对实现自然而精确的人机交互具有重要意义.然而,在针对手部自然动作范式的研究中,利用迁移学习提高模型在不同被试之间泛化能力的尝试仍然较少.本文选择掌握、指捏和旋拧三种手部自然动作开展脑电实验,并在实验数据集上验证了CA-MDM(协方差中心对齐-黎曼均值最小距离)和CA-JDA(协方差中心对齐-联合分布适应)这两种迁移学习算法的有效性.实验结果显示,CA-JDA在二分类和四分类任务中的平均准确率分别为60.51%±5.78%和34.89%±4.42%,而CA-MDM在相同分类任务中的表现分别为63.88%±4.59%和35.71%±4.84%.该结果凸显了基于黎曼空间的分类器在处理协方差特征时的优势.本文的研究不仅证实了迁移学习在手部自然动作范式中的可行性,也可为缩短BCI系统的校准时间,实现自然人机交互策略提供帮助.In the field of Brain-Computer Interface(BCI),the recognition of natural hand movements through electroencephalography(EEG)is crucial for achieving natural and precise human-machine interaction.However,attempts to enhance model generalization ability across different subjects using transfer learning are still rare in studies focusing on natural hand movement paradigms.Here,we investigate three natural hand movement paradigms of grasping,pinching and twisting through EEG experiments,and validate the effectiveness of two transfer learning algorithms,namely CA-MDM(Covariance matrix centroid Alignment-Minimum Distance to Riemannian Mean)and CA-JDA(Covariance matrix centroid Alignment-Joint Distribution Adaptation),on our experimental dataset.The results show that CA-JDA achieves average accuracies of 60.51%±5.78%and 34.89%±4.42%in binary and quadruple classification tasks,respectively,while CA-MDM performs at 63.88%±4.59%and 35.71%±4.84%in the same tasks,highlighting the advantages of Riemannian space-based classifiers in handling covariance features.This study not only confirms the feasibility of transfer learning in natural hand movement paradigms but also aids in reducing calibration time for BCI systems and implementing natural human-machine interaction strategies.

关 键 词：脑机接口 手部自然动作 迁移学习 黎曼几何 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TN911.7[自动化与计算机技术—控制科学与工程] R318[电子电信—通信与信息系统]