The utilization of motor imagery-based brain-computer interfaces (MI-BCI) has been shown to assist stroke patients activate motor regions in the brain. In particular, the brain regions activated by unilateral upper limb multi-task are more extensive, which is more beneficial for rehabilitation, but it also increases the difficulty of decoding. In this paper, self-attention convolutional neural network based partial prior transfer learning (SACNN-PPTL) is proposed to improve the classification performance of patients' MI multi-task. The backbone network of the algorithm is SACNN, which accords with the inherent features of electroencephalogram (EEG) and contains the temporal feature module, the spatial feature module and the feature generalization module. In addition, PPTL is introduced to transfer part of the target domain while preserving the generalization of the base model while improving the specificity of the target domain. In the experiment, five backbone networks and three training modes are selected as comparison algorithms. The experimental results show that SACNN-PPTL had a classification accuracy of 55.4%+/- 0.17 in four types of MI tasks for 22 patients, which is significantly higher than comparison algorithms (P < 0.05). SACNN-PPTL effectively improves the decoding performance of MI tasks and promotes the development of BCI-based rehabilitation for unilateral upper limb.
基金:
National Natural Science Foundation of China [82272612]; National High Level Hospital Clinical Research Funding and Elite Medical Professionals Project of China-Japan Friendship Hospital [ZRJY2021-QM02]; Young Elite Scientist Sponsorship Program By Bast [BYESS2023173]
第一作者机构:[1]Shanghai Jiao Tong Univ, Tong Ren Hosp, Sch Med, Dept Rehabil Med, Shanghai 200336, Peoples R China
通讯作者:
通讯机构:[1]Shanghai Jiao Tong Univ, Tong Ren Hosp, Sch Med, Dept Rehabil Med, Shanghai 200336, Peoples R China[2]Shanghai Jiao Tong Univ, Inst Rehabil, Sch Med, Shanghai 200025, Peoples R China
推荐引用方式(GB/T 7714):
Ma Jun,Ma Wanlu,Zhang Jingjing,et al.Partial prior transfer learning based on self-attention CNN for EEG decoding in stroke patients[J].SCIENTIFIC REPORTS.2024,14(1):doi:10.1038/s41598-024-79202-8.
APA:
Ma, Jun,Ma, Wanlu,Zhang, Jingjing,Li, Yongcong,Yang, Banghua&Shan, Chunlei.(2024).Partial prior transfer learning based on self-attention CNN for EEG decoding in stroke patients.SCIENTIFIC REPORTS,14,(1)
MLA:
Ma, Jun,et al."Partial prior transfer learning based on self-attention CNN for EEG decoding in stroke patients".SCIENTIFIC REPORTS 14..1(2024)