Transfer learning is provided with potential research value and application prospect in motor imagery electroencephalography (MI-EEG)-based brain-computer interface (BCI) rehabilitation system, and the source domain classification model and transfer strategy are the two important aspects that directly affect the performance and transfer efficiency of the target domain model. Therefore, we propose a parameter transfer learning method based on shallow visual geometry group network (PTL-sVGG). First, Pearson correlation coefficient is used to screen the subjects of the source domain, and the short-time Fourier transform is performed on the MI-EEG data of each selected subject to acquire the time-frequency spectrogram images (TFSI). Then, the architecture of VGG-16 is simplified and the block design is carried out, and the modified sVGG model is pre-trained with TFSI of source domain. Furthermore, a block-based frozen-fine-tuning transfer strategy is designed to quickly find and freeze the block with the greatest contribution to sVGG model, and the remaining blocks are fine-tuned by using TFSI of target subjects to obtain the target domain classification model. Extensive experiments are conducted based on public MI-EEG datasets, the average recognition rate and Kappa value of PTL-sVGG are 94.9% and 0.898, respectively. The results show that the subjects' optimization is beneficial to improve the model performance in source domain, and the block-based transfer strategy can enhance the transfer efficiency, realizing the rapid and effective transfer of model parameters across subjects on the datasets with different number of channels. It is beneficial to reduce the calibration time of BCI system, which promote the application of BCI technology in rehabilitation engineering.
迁移学习在基于运动想象脑电信号（MI-EEG）的脑机接口（BCI）康复系统中具有潜在的研究价值和应用前景，而源域分类模型及迁移策略是直接影响目标域模型性能与迁移效率的两个重要方面。为此，本文提出一种基于浅层视觉几何组网络（sVGG）的参数迁移学习（PTL）方法（PTL-sVGG）。首先，基于皮尔逊相关系数法对源域受试者进行筛选，并对优选的受试者MI-EEG数据进行短时傅里叶变换，获得时频谱图（TFSI）；然后，对视觉几何组网络-16（VGG-16）进行结构简化与模块化设计，并利用源域TFSI完成改进的sVGG模型预训练；进而，设计基于模块的冻结—微调迁移策略，快速寻找并冻结sVGG模型中贡献最大的某个模块，再基于目标受试者TFSI微调其余模块，获得目标域分类模型。基于公开脑电信号（EEG）数据库进行实验研究，PTL-sVGG取得的平均识别率和卡帕（Kappa）值分别为94.9%和0.898。结果表明，源域受试者优选有利于改善源域模型性能，基于模块的迁移策略有效提升了迁移效率，实现了基于不同导联数的数据库跨受试者间模型参数的快速有效迁移。这将有利于减少BCI系统的校准时间，促进BCI技术在康复工程中的应用。.
Keywords: Motor imagery; Parameter transfer learning; Pearson correlation coefficient; Transfer strategy; Visual geometry group network.