Electroencephalogram sleep staging method based on deep convolutional neural network

Abstract

The invention provides an electroencephalogram sleep staging method based on a deep convolutional neural network. The electroencephalogram sleep staging method comprises the following steps that S1, sleep signals of a subject are collected, and multi-lead electroencephalogram signals in the sleep signals are extracted; S2, performing data preprocessing on the electroencephalogram signals; S3, constructing and training an end-to-end deep convolutional neural network classifier; and S4, performing electroencephalogram sleep staging by using the deep convolutional neural network classifier. Compared with the conventional CNN electroencephalogram sleep staging method, the electroencephalogram sleep staging method provided by the invention has the advantages that under the condition of the sameiteration times and learning rate, each batch of the model adopts higher data, and the obtained output result is more stable. In terms of accuracy and F score, the method provided by the invention has better classification performance.

Description

technical field [0001] The invention relates to the technical field of EEG signal processing, in particular to an EEG sleep staging method based on a deep convolutional neural network. Background technique [0002] The negative effects of sleep disorder-related diseases such as obstructive sleep apnea (OSA) will accumulate from infancy to adulthood, causing irreversible damage to the body, such as unresponsiveness, craniofacial protrusion, etc. Sleep health monitoring such as polysomnography (PSG) and home portable EEG blood pressure devices are major tools for tracking patients with sleep disorders. Sleep staging includes dividing the polysomnographic records into 20-second or 30-second consecutive short periods, and marking the patient's EEG according to the sleep stage according to standardized classification rules, which usually requires a large number of human experts to mark the work, using computer methods Classifying EEG signals can help improve work efficiency. ...

AI Technical Summary

Problems solved by technology

[0012] Aiming at the problems that the current children's sleep staging method relies on feature extraction and preprocessing, and the accuracy needs to be improved, the present invention proposes an EEG sleep staging method based on a deep convolutional neural network

Images