Electroencephalogram consciousness dynamic classification method based on feature decision fusion of linear analysis

Abstract

The invention provides an electroencephalogram consciousness dynamic classification method based on feature decision fusion of linear analysis. The method comprises the steps: collecting an electroencephalogram signal data set X = (X1, X2,..., Xn) through a brain wave induction helmet, and n is a positive integer; classifying the signal data set X = (X1, X2,..., Xn) by using regular discriminant analysis (RDA) and secondary discriminant analysis (QDA) to obtain correlation coefficient matrixes rho RDA and rho QDA, and constructing feature decision fusion comprising a feature extraction unit, a projection classification unit and a decision selection unit to perform feature integration and decision selection on decisions and coefficients of RDA and QDA; therefore, good classification accuracy is obtained. According to the method, a more possibly accurate decision is selected by constructing feature decision fusion and integrating two algorithms, so that a relatively good classification accuracy rate is obtained on the aspect of motor imagery data classification.

Description

technical field [0001] The invention belongs to the field of electroencephalogram dynamic analysis, and in particular relates to an electroencephalogram consciousness dynamic classification method based on feature decision fusion of linear analysis. Background technique [0002] MI is an EEG signal, which reflects that specific functional areas of the brain are activated during motor imagination, and the corresponding EEG signals will produce stable and regular characteristic changes. Base. In order to decode the subject's intention from the MI signal, various methods have been proposed to identify and classify the MI signal, such as linear discriminant analysis (LDA), Gaussian classifier (Gaussian classifier), probabilistic neural network (probabilistic NN), etc. ). Especially for LDA-based methods, when classifying a new sample, it is projected onto the same straight line, and then the category of the new sample is determined according to the position of the projected po...

AI Technical Summary

Problems solved by technology

The disadvantage of QDA is that it cannot be used as a dimensionality reduction technique

Images