EEG classification method and system based on EEG classification based on Ou's alignment and PROCRUSESTES analysis

Abstract

The invention discloses a transfer learning method and system for EEG classification based on Euclidean alignment and Procrustes analysis, and belongs to the field of brain-computer interface based on motor imagery. Including: covariance alignment of the feature matrix of previous users and new users; mean alignment of feature matrices of previous users and new users; according to the feature matrix of previous users after the label and mean alignment of previous users, calculate the category center of previous users, Calculate the category center of the new user according to the pseudo-label of the new user and the feature matrix of the new user after the mean value alignment; construct the matrix of the category center of the previous user and the new user, and calculate the relationship between the category center of the new user and the new user through the orthogonal Platts analysis method. The rotation matrix corresponding to the center alignment of the categories of the previous users; the feature matrix of the new user after the mean alignment is multiplied by the rotation matrix to obtain the final 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