Brain intent recognition method and system based on brain-computer interface

Abstract

The present invention provides a brain intention recognition method based on a brain-computer interface, the method comprising: using MATLAB to construct an actual task model; performing experiments and collecting EEG information based on the actual task model to obtain an original EEG data set; Perform data preprocessing on a plurality of EEG data in the EEG raw data set to obtain a feature extraction matrix; input the EEG signal feature extraction matrix and corresponding labels into an extreme learning machine to obtain an extreme learning model; The predicted EEG data is input into the extreme learning model to obtain classification results. The invention improves the accuracy of recognizing brain intentions. The features of the electroencephalogram collected by the invention are more obvious after the co-space pattern feature is extracted, and it is easier to classify and identify. In addition, the present invention uses the model trained by the extreme learning machine as a classifier, which not only has a high accuracy rate, but also does not require cumbersome iterative calculations in the classification process, and has faster speed and better effect.

Description

technical field [0001] The invention relates to the technical field of biological signal processing and machine learning, in particular to a method and system for recognizing brain intentions based on a brain-computer interface. Background technique [0002] Brain-computer interface analyzes brain intentions by extracting scalp EEG signals, and then evaluates brain activity, which is of great significance for solving the medical rehabilitation problems of patients with movement disorders. [0003] In recent years, experts and scholars at home and abroad have carried out a series of research on brain-computer interface. There are three key steps in the research on brain intention recognition: designing reasonable experimental tasks, extracting features of EEG signals, and classifying EEG data. Among them, the establishment of a reasonable experimental task model is the first prerequisite for EEG signal extraction. In the study of brain-computer interface, experts at home and ...

AI Technical Summary

Problems solved by technology

In the rehabilitation of the motor nervous system, motor imagery is often used to induce EEG. However, if the experiment is performed under pure motor imagery for a long time, the subjects are prone to brain fatigue

The quality of the experimental data collected in this state is not high, which brings great pressure to the extraction of EEG signal features, and also reduces the accuracy of brain intention recognition

Images