南京信息工程大学学报2025，Vol.17Issue(2)：245-255,11.DOI:10.13878/j.cnki.jnuist.20240512002
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
摘要
Abstract
In the field of Brain-Computer Interface(BCI),the recognition of natural hand movements through elec-troencephalography(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 stud-ies 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 al-gorithms,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 re-sults show that CA-JDA achieves average accuracies of 60.51%±5.78%and 34.89%±4.42%in binary and quad-ruple 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 re-ducing 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Key words
brain-computer interface(BCI)/natural hand movements/transfer learning/Riemannian geometry分类
计算机与自动化引用本文复制引用
薛沐辉,徐宝国,李浪,宋爱国..基于迁移学习的手部自然动作脑电识别[J].南京信息工程大学学报,2025,17(2):245-255,11.基金项目
国家重点研发计划(202022YFC2405602) （202022YFC2405602）
江苏省前沿引领技术基础研究专项(BK20192004A) （BK20192004A）
江苏省自然科学基金(BK20221464) （BK20221464）
