Sleep staging method based on BLSTM and sleep staging device based on BLSTM

Abstract

The invention provides a sleep staging method based on BLSTM and a sleep staging device on the BLSTM. The BLSTM comprises two training layers and one output layer, wherein each training layer comprises 16 units, the output layer comprises 4 units, and the four units correspond to an awakening stage, a light sleep stage, a deep sleep stage and a rapid eye movement stage of sleep respectively; and input characteristics of the BLSTM comprise a characteristic extracted from an RR interphase signal, a characteristic extracted from a breathing signal and a characteristic extracted from cardiopulmonary coupling. The method and device acquire cardiopulmonary signals of a testee using a low-cost wearable multi-sensor system, conduct four-classification sleep staging by a bidirectional recursive neural network model which has an LSTM function and realize accurate staging of sleep.

Description

technical field [0001] This application relates to a sleep staging technique. Background technique [0002] Sleep quality is crucial to human health. Sleep quality is usually analyzed using physiological signals, which are not only related to physiological functions, but also have different patterns. Although there are multiple standards for sleep stages, the most common four-category sleep stage includes wakefulness, light sleep, deep sleep, and rapid eye movement. For example, deep sleep helps the body's metabolism and wound healing, while dreaming mostly occurs during rapid eye movement. Accurate sleep staging is important for sleep architecture to diagnose and restore sleep disorders. [0003] PSG is a standard method of sleep quality analysis, which can provide myoelectric activity in various parts of the body and has been used for sleep staging for the past few decades. This sleep staging method mainly relies on EEG signals, eye movement signals and myoelectric sig...

AI Technical Summary

Problems solved by technology

At the same time, the traditional support vector machine algorithm was used to perform four-category sleep staging on the cardiopulmonary eigenvalues ​​of 48 subjects with a step size of 30 seconds, and the accuracy and prediction accuracy were relatively low

Images