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

Deep learning-based method for examining mouth and nose breathing

A deep learning, mouth and nose technology, applied in the field of biomedicine, can solve problems that affect facial development, lack of inspection and classification of mouth, nose and breathing, and discomfort of the patient's head or face

Pending Publication Date: 2021-11-09
GUANGDONG UNIV OF TECH
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Third, in addition to affecting facial development, children who breathe through the mouth for a long time are also more likely to suffer from obstructive sleep apnea syndrome. However, there is no way to check and classify mouth and nose breathing. There are wearable breathing sensors in the market. Wearing it for a long time will cause discomfort to the patient's head or face
This invention is an external device that monitors the patient's breathing through the nasal flow channel and the oral flow channel. Wearing it for a long time will cause discomfort to the patient's head or face.

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
  • Deep learning-based method for examining mouth and nose breathing
  • Deep learning-based method for examining mouth and nose breathing
  • Deep learning-based method for examining mouth and nose breathing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] like figure 1 As shown, a method for examining mouth and nose breathing based on deep learning includes the following steps:

[0057] S1: Segment the respiratory signal to obtain an effective sound segment;

[0058] S2: Use the Mel frequency cepstral coefficient extraction method improved by the empirical mode decomposition method to extract the features of the effective sound segment and obtain the feature set;

[0059] S3: Use a recurrent convolutional neural network to divide the feature set into a training set and a test set, and obtain a high classification accuracy model through five-fold cross-validation to check the mouth and nose breathing.

[0060] In the above solution, the effective sound segment of the breathing signal can be segmented to extract the effective sound segment, so that the processing of the breathing sound is more targeted. Due to the non-stationary signal of the sound signal, the method of empirical mode decomposition suitable for non-stati...

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 relates to a deep learning-based method for examining mouth and nose breathing, which comprises the following steps of: segmenting a breathing signal to obtain an effective sound segment; performing feature extraction on the effective sound segments by using a Mel-frequency cepstrum coefficient extraction method improved by an empirical mode decomposition method; and dividing the feature set into a training set and a test set by using a cyclic convolutional neural network, and performing five-fold cross validation to obtain a high-classification-precision model to examine mouth and nose breathing. The effective sound segments of the respiratory signal can be segmented to extract the effective sound segments, so that the processing of the respiratory sound has pertinence. Effective sound segments are decomposed by introducing an empirical mode decomposition method of non-stationary signals, multi-scale analysis can be performed on the signals, and feature extraction is performed on the effective sound segments by using an improved Mel-frequency cepstrum coefficient extraction method. And the feature set is divided into a training set and a test set by using a cyclic convolutional neural network, and five-fold cross validation is performed to obtain a high-classification-precision model to examine mouth and nose breathing.

Description

technical field [0001] The invention relates to the field of biomedicine, and more specifically, to a deep learning-based method for checking mouth and nose breathing. Background technique [0002] Respiration is the process of gas exchange between the human body and the external environment. For some patients with severe lung disease, they need breathing aids to help them breathe. Humans have two breathing patterns. They are nasal and oral breathing patterns. In fact, we don't want to breathe through our mouths for a few reasons. It is necessary and meaningful for us to classify the sources of breathing signals for the following reasons. First of all, if people breathe through their mouth for a long time, because the mouth is not the respiratory organ of the human body, then those who breathe through the mouth cannot get oxygen into the lungs well, so there is a certain possibility that their brains are starved of oxygen, and when When the brain of these people is hypo...

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): G10L25/66G10L25/24G10L25/30A61B5/08
CPCG10L25/66G10L25/24G10L25/30A61B5/08
Inventor 廖国钊凌永权叶琪
Owner GUANGDONG 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