Deep learning-based method for examining mouth and nose breathing

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...

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.

Images