Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Human body sleep stage estimating method based on deep learning network

A deep learning network, sleep stage technology, applied in the fields of medical health and information, can solve problems such as the inability to automatically realize feature optimization, and achieve the effect of improving estimation performance

Inactive Publication Date: 2019-02-12
DALIAN UNIV OF TECH
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The above methods mostly use artificially designed signal features for classification, and cannot automatically realize feature optimization in order to obtain the best sleep stage estimation performance. There are deficiencies in the automation of sleep stage estimation, diversification of input parameters, and performance optimization.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Human body sleep stage estimating method based on deep learning network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The specific implementation of the present invention will be described in detail below in combination with the technical scheme and the accompanying drawings.

[0035] The embodiment adopts such as figure 1 The system structure shown. Heart rate, respiratory rate, body movement, snoring, and EEG signals are used to collect 5 sensor signals, and 100Hz sampling frequency is used to collect sensor signals from various channels, and a 10Hz low-pass filter is used to filter the signals in time domain to eliminate high-frequency interference. The signal time series collected by each sensor is subjected to 1024-point fast Fourier transform to obtain the frequency domain signal sequence. Based on the time domain sequence and frequency domain sequence obtained by each sensor, the time-frequency vector of the sensor is formed after smoothing filtering and down-sampling, which is sent to the to deep learning networks. The deep learning network adopts a 4-layer fully connected st...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a human body sleep stage estimating method based on a deep learning network, and belongs to the technical field of medical treatment and health and information. According to themethod, the sleep stage where the human body is in can be estimated, and an effective method for analyzing the sleep stage is provided for the fields of chronic patients, elder monitoring, health surveillance and the like. According to the method, by means of one or more kinds of information of the human body heart rate, respiratory rate, body moving, snores, electroencephalogram signals and thelike collected by a sensor, the optimal features of the information are extracted through the deep learning network, and a Softmax classifier is adopted for estimating the sleep stage based on the optimal features. According to the method, the estimating performance of the human body sleep stage can be improved, and the health state of the human body is effectively monitored.

Description

technical field [0001] The invention belongs to the field of medical health and information technology, and relates to a method for estimating human sleep stages based on a deep learning network. This method uses one or more information such as human heart rate, respiratory rate, body movement, snoring, and EEG signals collected by sensors, extracts the optimal features of these information through a deep learning network, and estimates the sleep stage based on the optimal features. . The invention can estimate the sleep stage of the human body, and provides an effective method for analyzing the sleep stage in the fields of chronic patient and elderly monitoring, health monitoring and the like. Background technique [0002] Sleep quality is closely related to a person's health status. By estimating the sleep stage of the human body, it can effectively monitor the health status of the human body, so as to realize the monitoring of chronic patients and the elderly. [0003] ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): A61B5/00
CPCA61B5/4809A61B5/4812A61B5/4815A61B5/7257A61B5/7267
Inventor 高庆华王洁马晓瑞
Owner DALIAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com