EEG classification transfer learning method and system based on Euclidean alignment and Procuses analysis

Abstract

The invention discloses an EEG classification transfer learning method and system based on Euclidean alignment and Procuses analysis, and belongs to the field of brain-computer interfaces based on motor imagery. The method comprises the following steps: performing covariance alignment on previous user and new user feature matrixes; performing mean value alignment on the feature matrixes of the previous users and the new users; calculating the category center of the previous user according to the label of the previous user and the feature matrix of the previous user after the mean value is aligned, and calculating the category center of the new user according to a pseudo label of the new user and the feature matrix of the new user after the mean value is aligned; constructing a previous user and new user category center matrix, and calculating a rotation matrix for aligning the category center of the new user with the category center of the corresponding previous user through an orthogonal Principal analysis method; and multiplying the feature matrix and the rotation matrix of the new user after mean value alignment to obtain finally aligned new user data.

Description

technical field [0001] The invention belongs to the field of brain-computer interface based on motor imagery, and more specifically, relates to a transfer learning method and system for EEG (electroencephalogram) classification based on Euclidean alignment and Procrustes analysis (Platts analysis). Background technique [0002] Migration learning is to use the labeled data of other related tasks to improve the learning performance when the target task has no or only a small amount of labeled data. For example, in the field of BCI based on motor imagery, it is difficult for a system trained based on previous user data to correctly judge the intention of a new user due to large differences between different users. Therefore, new users need to go through a lengthy calibration process before using it. However, past user data is still helpful for data classification of new users, so transfer learning can use past user data to improve the performance of the system on new users. ...

AI Technical Summary

Problems solved by technology

[0004] However, the Riemann Platts analysis method has high computational complexity and takes a long time; and the Riemann Platts analysis needs to know a certain number of sample labels in the target domain before it can work

Images