Motion imagination electroencephalogram classification model training method and system based on transfer learning

The invention provides a transfer learning-based motor imagery electroencephalogram classification model training method, which comprises the following steps of: acquiring electroencephalogram signals of a target user and an auxiliary user, extracting signal features of the electroencephalogram signals, and constructing a total data set; the total data set comprises an auxiliary user data set and a target user data set; segmenting the auxiliary user data set into a plurality of data subsets, and constructing an auxiliary domain data set; the target user data set is a target domain data set; and training by a transfer learning method through the auxiliary domain data set and the target domain data set to obtain a motor imagery electroencephalogram classification model. The invention further provides a motor imagery electroencephalogram classification model training system based on transfer learning and a data processing device for motor imagery electroencephalogram classification model training. 本发明提出一种基于迁移学习的