Motor imagery electroencephalogram signal classification method and system

Abstract

The invention provides a motor imagery electroencephalogram signal classification method and a system. The method comprises the following steps: extracting and classifying time-space characteristics of motor imagery electroencephalogram original data by using a first classification model; performing time-space feature extraction and classification on the motor imagery electroencephalogram differential entropy by using a second classification model; performing time-space feature extraction and classification on the motor imagery electroencephalogram likelihood entropy by using a third classification model; and fusing the classification results of different dimensions to obtain a final classification result. According to different signals, respective processing is carried out, feature classification results of different dimensions are fused, and the classification precision of the motor imagery electroencephalogram signals can be improved.

Description

technical field [0001] The invention belongs to the technical field of information classification, and in particular relates to a method and system for classifying motor imagery EEG signals. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] With the development of machine learning and deep learning, more and more training models have entered the public view, including CNN, SVM, etc. These models are widely used in information processing, classification and analysis. [0004] EEG motor imagery is to analyze the collected EEG through brain-computer interface technology, so as to infer the subject's thoughts when collecting signals, and convert the subject's original intention into command signals to communicate with external devices. That is to connect the brain with external devices and establish a communication system that enables it to exc...

AI Technical Summary

Problems solved by technology

[0005] However, according to the inventor's understanding, existing research methods such as SVM, CNN, LSTM and other methods need to do preprocessing operations, the process is relatively cumbersome and complicated, the response time is slow, and the feature extraction process is not enough, resulting in the EEG motion imagery signal The response speed is slow, and the classification accuracy cannot meet the requirements

Images