Electroencephalogram feature extraction method based on CSP and R-CSP algorithms

Abstract

The invention relates to an electroencephalogram feature extraction method based on CSP and R-CSP algorithms. According to the electroencephalogram feature extraction method, when a traditional CSP algorithm is used for extracting small sample electroencephalograms, covariance estimation of the traditional CSP algorithm will generate a larger error; according to the electroencephalogram feature extraction method, the traditional CSP algorithm is improved, and the regularization CSP algorithm R-CSP is put forward. Firstly, a small wave threshold denoising algorithm is used for conducting de-noising processing; secondly, covariance matrixes of five experimenters are solved, one target experimenter is selected, and the rest of the experimenters are auxiliary experimenters, an optimal spatial filter is constructed through selection of regularization parameters, and feature vectors are accordingly extracted; and finally, a genetic algorithm is used for optimizing a support vector machine classifier, and the correct rate of the classification result is further improved. The final classification result shows that the R-CSP algorithm is better in correct rate of the classification result compared with a traditional CSP algorithm.

Description

technical field [0001] The invention relates to a method for extracting features of electroencephalogram signals, in particular to a method for extracting features of electroencephalogram signals based on CSP and R-CSP algorithms. Background technique [0002] The brain is a complex system composed of hundreds of millions of neurons, which are responsible for the coordinated operation of various functions of the human body. The potential activity of brain cell groups recorded through electrodes on the cerebral cortex is called Electroencephalogram (EEG). After preprocessing, feature extraction, classification and recognition, the collected EEG signals are finally input into a computer or related electronic equipment, and the external equipment makes corresponding actions by interpreting different states of consciousness of the human brain. - Implementation process of Brain Computer Interface (BCI) technology. BCI can bring some people who are unable to move but have a clear...

AI Technical Summary

Problems solved by technology

[0004] In the EEG acquisition experiment, if the number of training samples collected is relatively small, the covariance estimation may produce adverse effects when using the traditional CSP algorithm for feature extraction, and the EEG signal itself is a low signal-to-noise ratio. signal, which will make the estimated variance higher, which will affect the feature extraction of EEG signal

Secondly, because the small sample data needs to be collected many times, and when the collection time is too long or the number of times is too high, many factors such as the emotional and physical conditions of the subjects will affect the reliability of the data, resulting in the redundancy of the collected data. , will affect the classification results

Images