Motor imagery electroencephalogram signal classification method based on hybrid model

Abstract

The invention provides a motor imagery electroencephalogram signal classification method based on a hybrid model. The motor imagery electroencephalogram signal classification method comprises the following steps: S1, data extraction: collecting two groups of data from a database as an electroencephalogram database; s2, data reconstruction: normalizing electroencephalogram data in an electroencephalogram database, and storing the normalized electroencephalogram data in a four-dimensional tensor structure; s3, feature optimization: optimizing the electroencephalogram data by using an ODV-CSSD algorithm to obtain an optimal electroencephalogram feature; and S4, forming an interpretable cluster by using the prior information, establishing a decision boundary, and obtaining a final category attribution result. The invention provides a novel motor imagery electroencephalogram signal classification method aiming at the problem that a common space mode is too sensitive to abnormal data so that overfitting is prone to occurring, and a novel feature optimization algorithm ODV-CSSD is provided and researched. According to the method, the optimal electroencephalogram feature can be obtained, and meanwhile, the dimension of the optimal electroencephalogram feature can be achieved, so that extraction and classification of the left-hand and right-hand motor imagery electroencephalogram signals are realized, and the recognition accuracy is improved.

Description

technical field [0001] The invention relates to the field of electroencephalogram signal classification, in particular to a motor imagery electroencephalogram signal classification method based on a mixed model. Background technique [0002] The human brain is composed of interconnected neurons, and as the electrical signals generated by the activities between neurons, the electroencephalogram (Electroencephalogram, EEG) records the electrical signal changes during brain activity, which is the electrophysiological activity of brain nerve cells in the cerebral cortex. Or the general reflection of the surface of the scalp. Brain-Computer Interface (BCI) technology converts such electrical signals into control commands, thereby providing a communication path between the brain and external devices (such as BCI wheelchairs, prosthetics, and robotic arms). [0003] The core of BCI technology is to adjust the mutual adaptive control relationship between the human brain and the mac...

AI Technical Summary

Problems solved by technology

[0004] At present, a large number of researches at home and abroad are devoted to the extraction and classification of EEG features in the spatial domain, and the design of spatial filters to improve the quality of EEG signals and extract features. The more representative algorithm is Common Spatial Pattern (CSP), This method is widely used in EEG signal processing by finding a set of spatial filters to maximize the variance of a certain category and minimize the other category, but this method has certain limitations. Too sensitive, when the number of samples in the training set is small, it will lead to data overfitting, which makes CSP extremely susceptible to noise interference

Images