Ma Jun, Yang Banghua, Rong Fenqi, Gao Shouwei, Wang Wen
School of Mechatronic Engineering and Automation, School of Medicine, Research Center of Brain-Computer Engineering, Shanghai University, Shanghai, 200444 China.
Department of Radiology & Functional and Molecular Imaging Key Lab of Shaanxi Province, Tangdu Hospital, Fourth Military Medical University, Xi'an, 710038 Shaanxi China.
Cogn Neurodyn. 2024 Oct;18(5):2521-2534. doi: 10.1007/s11571-024-10100-5. Epub 2024 Apr 10.
Transfer learning is increasingly used to decode multi-class motor imagery tasks. Previous transfer learning ignored the optimizability of the source model, weakened the adaptability to the target domain and limited the performance. This paper first proposes the multi-loss fusion convolutional neural network (MF-CNN) to make an optimizable source model. Then we propose a novel source optimized transfer learning (SOTL), which optimizes the source model to make it more in line with the target domain's features to improve the target model's performance. We transfer the model trained from 16 healthy subjects to 16 stroke patients. The average classification accuracy achieves 51.2 ± 0.17% in the four types of unilateral upper limb motor imagery tasks, which is significantly higher than the classification accuracy of deep learning ( < 0.001) and transfer learning ( < 0.05). In this paper, an MI model from the data of healthy subjects can be used for the classification of stroke patients and can demonstrate good classification results, which provides experiential support for the study of transfer learning and the modeling of stroke rehabilitation training.
迁移学习越来越多地用于解码多类运动想象任务。以往的迁移学习忽略了源模型的可优化性，削弱了对目标域的适应性，限制了性能。本文首先提出多损失融合卷积神经网络（MF-CNN）以构建可优化的源模型。然后我们提出了一种新颖的源优化迁移学习（SOTL），它对源模型进行优化，使其更符合目标域的特征，以提高目标模型的性能。我们将从16名健康受试者训练的模型迁移到16名中风患者身上。在四种类型的单侧上肢运动想象任务中，平均分类准确率达到51.2±0.17%，显著高于深度学习的分类准确率（<0.001）和迁移学习的分类准确率（<0.05）。本文中，来自健康受试者数据的运动想象模型可用于中风患者的分类，并能展示出良好的分类结果，这为迁移学习研究和中风康复训练建模提供了经验支持。
