Spatial auditory induction P300 electroencephalogram signal recognition method and device

Abstract

The invention discloses a spatial auditory induction P300 electroencephalogram signal recognition method and device, and relates to the field of algorithm study. The method and the device are used forsolving the problems that the existing convolutional neural network is limited by data volume; a serious overfitting phenomenon can easily occur; and the recognition result is not good. The method comprises the following steps of preprocessing a collected P300 electroencephalogram signal to obtain an original signal; obtaining a plurality of IMF components from the original signal through an EMDalgorithm; obtaining a denoising electroencephalogram signal through calculating the IMF components and normalizing the autocorrelation function variance; inputting the denoising electroencephalogramsignal into a convolutional layer of the convolutional neural network to obtain a space feature of the denoising electroencephalogram signal; gathering the space features obtained by the convolutionallayer to form global features; inputting the global features into a whole connection layer of the convolutional neural network; and outputting the classification accuracy by an output layer of the convolutional neural network.

Description

technical field [0001] The invention relates to the field of algorithm research, and more particularly to a method and device for identifying a spatial auditory-induced P300 electroencephalographic signal. Background technique [0002] The brain is the highest nerve center in the human body and controls various life activities of the human body. With the increase of cerebral palsy, brainstem stroke, spinal cord injury and other diseases in recent years, many patients have partially or completely lost the ability to control their muscles voluntarily. The brain-computer interface aims to realize a platform that does not rely on peripheral nerves and muscle tissue to directly connect the brain and the computer, which can help such patients recover and improve their quality of life. For healthy people, the brain-computer interface system, as a brand-new interaction method, will greatly enrich people's entertainment and communication methods. It also has important applications ...

AI Technical Summary

Problems solved by technology

[0008] The embodiment of the present invention provides a spatial auditory-induced P300 EEG signal recognition method and device to solve the problem that the existing convolutional neural network is limited by the amount of data, prone to severe overfitting, and the recognition result is not good question

Images