Method and device for classifying active brain-computer interaction system motor imagery tasks

Abstract

The invention belongs to the technical field of brain-computer interaction (BCI), and particularly relates to a method and device for classifying active brain-computer interaction system motor imagery tasks. The method and device for classifying active brain-computer interaction system motor imagery tasks resolve the technical problems that an existing classification mode for the active motor imagery tasks is not high in accuracy and long in execution time. The classification method for the active BCI system motor imagery tasks comprises the steps that (1) original brain electrical signals in the training period are collected; (2) processing and characteristic extraction are carried out on the brain electrical signals, and the detection threshold Vd is calculated; (3) collection and state detection are carried out on the brain electric signals in the active imagery period, and the idle state and the imagery motion state of the brain are detected according to the threshold; (4) the motor imagery brain electric characteristics are classified into left hand motor imagery tasks and right hand motor imagery tasks. The brain electric characteristic classification method which combines threshold detection and supporting of a support vector machine is stable and reliable, improves the accuracy of classifying the motor imagery brain electric characteristics, and effectively shortens the classification execution time.

Description

technical field [0001] The invention belongs to the technical field of brain-computer interaction, in particular to a method and device for classifying motor imagery tasks of an active brain-computer interaction system. Background technique [0002] Brain-computer interaction technology (BCI) is a communication system established between the human brain and external devices that does not depend on the conventional peripheral nerve and muscle systems of the brain. It uses computers and other equipment to analyze the EEG data collected under specific tasks, converts brain information into control commands, and realizes communication between people and the outside world and control of the external environment. The BCI system provides a new way of communication and control, which has brought good news to those paraplegics who have physical disabilities but clear brains. It can help people with severe physical disabilities to restore the ability to communicate with the outside w...

AI Technical Summary

Problems solved by technology

[0005] At present, the motor imagery EEG feature recognition methods mainly include the classifier detection method based on Bayesian linear discrimination. The correct rate and mean square error of the classification results of the test set samples are 77.62% and 0.495 respectively, and the feature extraction process requires common spatial frequencies. The pattern algorithm and ARMA spectrum estimation method extract the spatial domain and frequency domain features of the sample, and their real-time performance is poor

Zhao Li, Wang Lei and others used the phenomenon of blocking the α wave generated by opening the eyes and increasing the energy of the α wave caused by closing the eyes, and designed an active BCI system to distinguish the subject's imaginary movement state from the idle state, but this method requires More EEG leads and the cooperation of subjects, and are easily affected by blinking; George et al. adopted offline training, based on the idea of ​​maximizing the correct discrimination rate of two types of motor imagery and minimizing the false discrimination rate of idle state, using However, it is difficult to obtain effective and fully meaningful idle state training samples in practical applications, and the online motor imagery EEG feature classification takes a lot of time, so it is relatively difficult in practical applications. big limit

Images