Sleep apnea detection method and system based on multistage wavelet coding and decoding

A sleep apnea detection method technology, applied in the field of biomedicine, can solve the problems of not taking into account the correlation of breathing properties, the positioning accuracy of apnea events needs to be improved, and achieve the effect of simple and reliable methods

Pending Publication Date: 2021-10-15
成都乐享智家科技有限责任公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this scheme is also used to accurately detect apnea events during sleep, the scheme does not take into account the correlation between the nature of breathing before and after, and the accuracy of feature extraction and the positioning accuracy of apnea events need to be improved

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
  • Sleep apnea detection method and system based on multistage wavelet coding and decoding
  • Sleep apnea detection method and system based on multistage wavelet coding and decoding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] In this example, if figure 1 As shown, a sleep apnea detection method based on multilevel wavelet encoding and decoding comprises the following steps:

[0038] Step 1: Signal standardization, collect two sleep BCG signals of the user, and perform standardized preprocessing on the collected BCG signals to obtain standardized signals;

[0039] Step 2: Wavelet decomposition training, constructing the NWCNN deep neural network, inputting standardized signals into the NWCNN deep neural network for wavelet decomposition training, and obtaining the output of NWCNN, that is, the deep neural network model;

[0040] Step 3: Model fine-tuning, using the collected BCG signal as sample data and dividing the sample data into training set and test set, pre-training and fine-tuning the deep neural network;

[0041] Step 4: Train the HMM model, segment the training set in step 3 based on the duration of 1 minute, and train the HMM model based on the segmented data;

[0042] Step 5: Ev...

Embodiment 2

[0056] In this embodiment, a sleep apnea detection method based on multi-level wavelet codec includes the following steps:

[0057] Step 1: Signal standardization, collect two sleep BCG signals of the user, and perform standardized preprocessing on the collected BCG signals to obtain standardized signals;

[0058] Step 2: Wavelet decomposition training, constructing the NWCNN deep neural network, inputting standardized signals into the NWCNN deep neural network for wavelet decomposition training, and obtaining the output of NWCNN, that is, the deep neural network model;

[0059] Step 3: Model fine-tuning, using the collected BCG signal as sample data and dividing the sample data into training set and test set, pre-training and fine-tuning the deep neural network;

[0060] Step 4: Train the HMM model, segment the training set in step 3 based on the duration of 1 minute, and train the HMM model based on the segmented data;

[0061] Step 5: Event location, input the original BCG...

Embodiment 3

[0073] In this embodiment, in order to realize the sleep apnea detection method of Embodiment 1 and Embodiment 2, a sleep apnea detection system based on multi-level wavelet coding and decoding is provided, including a signal acquisition unit, a signal preprocessing unit, an integrated simulation The front end, data forwarding unit, power management module, microprocessor and host computer; the signal acquisition unit is connected with the signal preprocessing unit; the signal preprocessing unit is connected with the integrated analog front end; the integrated analog front end is connected with the microprocessor; the microprocessor and The data forwarding unit is connected; the data forwarding unit establishes a communication connection with the host computer through the communication network.

[0074] In this embodiment, the signal acquisition unit is a piezoelectric ceramic sensor, which is used to acquire the BCG signal when the user is sleeping.

[0075] In this embodimen...

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 discloses a sleep apnea detection method and system based on multistage wavelet coding and decoding. The method comprises the following steps: collecting a sleep BCG signal, and carrying out the standardization preprocessing of the sleep BCG signal to obtain a standardized signal; constructing an NWCNN deep neural network, and inputting the standardized signal into the network for training to obtain the output of the NWCNN; dividing the collected BCG signals serving as sample data into a training set and a test set, and performing pre-training and fine tuning on the network; segmenting the training set by taking the duration of 1 minute as a segmentation basis, and training an HMM model according to segmented data; and inputting the BCG signal into the network for noise reduction and feature extraction, inputting the extracted features into the HMM model, obtaining a sleep apnea classification probability, and positioning a sleep apnea event. According to the method, feature extraction and classification are carried out based on the multi-stage wavelet convolution coding and decoding network, and the effects of noise reduction and feature extraction and classification are achieved based on the original BCG signal.

Description

technical field [0001] The invention relates to the field of biomedicine, in particular to a sleep apnea detection method and system based on multilevel wavelet coding and decoding. Background technique [0002] In the current biomedical engineering research, we collect and process various physiological signals of the human body. Among them, the electrocardiographic signal is a kind of physiological signal, and the information contained in it is of great significance to the diagnosis of heart disease. [0003] The current conventional non-contact detection method based on a single signal source and distinguishing apnea after the event does not consider the correlation of the nature of the breath before and after, the detection accuracy is low, and it cannot detect, warn and locate in time. [0004] For example, the patent application with the application number CN201911413560.9 discloses a signal detection system for judging sleep apnea. The signal detection method includes...

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
Patent Type & Authority Applications(China)
IPC IPC(8): A61B5/08A61B5/00
CPCA61B5/0826A61B5/4818A61B5/726A61B5/7264A61B5/7267A61B5/7203A61B5/725
Inventor 魏开航邓韩彬蒙俊甫张其飞夏林刘毅曾东
Owner 成都乐享智家科技有限责任公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap