Deep learning model based on multi-scale network and application in brain state monitoring

Abstract

A deep learning model based on a multi-scale network and application in brain state monitoring are provided. A model establishing method comprises steps of: preprocessing and multi-scale transforming a measured multichannel signal; obtaining a multi-scale weighted recursive network and a cross-recursive rate matrix corresponding to the multi-scale weighted recursive network of the multichannel signal in all scales; extracting the network indexes of the multi-scale weighted recursive network at different scales; at each scale, retaining relatively large elements in the cross recursive rate matrix and obtaining an unweighted adjacent matrix and a multi-scale unweighted recursive network corresponding thereto; for each value of a variable in the set range, obtaining the multi-scale unweighted recursive network and the adjacent matrix corresponding to the multi-scale unweighted recursive network, extracting the network indexes of the multi-scale unweighted recursive network at different scales, calculating the integral of the network indexes when the variable is changed in the set range, and the integral as the final network index of the multi-scale unweighted recursive network under each scale; and training the deep learning model and monitoring a brain state.

Description

technical field [0001] The invention relates to a brain state monitoring method. In particular, it relates to a multi-scale network-based deep learning model for multi-channel EEG signals and its application in brain state monitoring. Background technique [0002] EEG signals are the overall reflection of the physiological activities of brain nerve cells on the surface of the cerebral cortex or scalp. EEG signals contain a large amount of physiological and disease information. In clinical medicine, accurate identification of brain states can not only provide diagnosis basis for some brain diseases, but also provide effective treatment for some brain diseases. In terms of engineering applications, people are also trying to use EEG signals to realize brain-computer interfaces, using the differences in EEG signals for different sensations, movements or cognitive activities, and realizing ideas through effective extraction and classification of EEG signal features. control etc...

AI Technical Summary

Problems solved by technology

However, most current time series analysis methods can only analyze unary data. How to integrate multi-channel information obtained by multi-channel sensors to achieve more accurate identification and provide important basis for disease diagnosis still has great limitations. It is still a problem worth exploring for the realization of more complex mind control

Images