Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and system for breath detection realized by cgan and multi-scale convolutional neural network

A convolutional neural network and breathing detection technology, applied in CGAN and multi-scale convolutional neural network to realize breathing detection and system field, can solve the problems of high environmental noise interference and low detection accuracy, and achieve low detection accuracy requirements and guarantee The effect of cleanliness

Active Publication Date: 2022-06-17
SICHUAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of the problems of the above research, the purpose of the present invention is to provide a method and system for realizing breath detection by CGAN and multi-scale convolutional neural network, so as to solve the problem that the existing detection is greatly disturbed by environmental noise, thus making the detection accuracy low

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
  • Method and system for breath detection realized by cgan and multi-scale convolutional neural network
  • Method and system for breath detection realized by cgan and multi-scale convolutional neural network
  • Method and system for breath detection realized by cgan and multi-scale convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0071] The invention proposes a CSI signal with human breathing shock collected by common Wi-Fi equipment, denoising the CSI through CGAN, and then using a multi-scale convolutional neural network to extract the signal period for human breathing detection. Real-time monitoring of abnormal breathing can be widely used in family hospitals and other environments.

[0072] The main process of the present invention includes: 1) CSI data acquisition with respiratory shock; 2) generation of noise-free power spectrum; 3) channel CSI data noise reduction processing; 4) establishment of human respiratory CSI model; 5) multi-scale neural network Extract the CSI periodically varying angular velocity; 6) estimate the respiration rate according to the periodically varying angular velocity. The specific implementation steps are as follows:

[0073] 1. Acquisi...

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 method and system for realizing breath detection by CGAN and a multi-scale convolutional neural network, which belongs to the field of medical health and deep learning, and solves the problem that the existing detection is greatly disturbed by environmental noise, thereby making the detection accuracy low. The invention includes: 1) acquisition of CSI data with respiratory impact; 2) generation of noise-free power spectrum diagram; 3) noise reduction processing of channel CSI data; 4) establishment of human respiration CSI model; 5) multi-scale neural network extraction of CSI period Changing the angular velocity; 6) Estimating the respiration rate according to the periodically varying angular velocity. The invention is used for detection of human respiration.

Description

technical field [0001] A method and system for realizing breath detection by CGAN and multi-scale convolutional neural network, which are used for human breath detection, and belong to the field of medical health and deep learning. Background technique [0002] Respiration is one of the most important life activities of human beings. Respiration frequency is an important indicator for judging human health and an early manifestation of physiological deterioration. Real-time detection of respiration frequency can timely and effectively feedback the health status of the human body and prevent the occurrence of diseases. Especially for some people with respiratory diseases, real-time detection of respiratory conditions is necessary. Obtaining human respiratory information to prevent dangerous situations often requires professional respiratory testing equipment. In the past, respiratory detection equipment was generally used for real-time respiratory monitoring of patients. For ...

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 Patents(China)
IPC IPC(8): A61B5/08A61B5/00G06N3/04G06N3/08
CPCA61B5/0816A61B5/7203A61B5/7267G06N3/08G06N3/045
Inventor 魏骁勇吴柳繁张栩禄杨震群
Owner SICHUAN UNIV