Lung sound classification method and system based on deep learning, and storage medium

Abstract

The invention discloses a lung sound classification method and system based on deep learning and a storage medium, and the method comprises the steps: collecting a to-be-tested lung sound signal, and carrying out the preprocessing of the to-be-tested lung sound signal; performing feature extraction on the preprocessed lung sound signal to be tested based on a wavelet transform method to obtain a lung sound feature matrix to be tested; uniformly extracting a plurality of training lung sound feature matrixes with known classification results from a sample database, and training a deep convolutional neural network by using the plurality of training lung sound feature matrixes; and importing the to-be-tested lung sound feature matrix into a trained deep convolutional neural network for feature matching, and outputting a classification result of the to-be-tested lung sound signal. In the embodiment of the invention, the deep convolutional neural network is used for carrying out multi-class feature recognition on the lung sound signal, and a good classification effect is achieved.

Description

technical field [0001] The present invention relates to the technical field of biomedical signal recognition, in particular to a lung sound classification method, system and storage medium based on deep learning. Background technique [0002] As a physiological signal produced by the human respiratory system and the external environment in the gas exchange, the lung sound signal contains rich pathological and physiological information. With the advent of the stethoscope, clinicians use it as a means of diagnosing lung diseases. From a doctor's point of view, it is based on the volume, sound thickness, and delay length of breath sounds to judge the pathological conditions of the human lungs. The test results are bound to be biased. Compared with the subjective auscultation method, many scholars have paid attention to the computer-aided analysis of lung sound signals, such as using the Mel frequency cepstral coefficient that characterizes the auditory characteristics of the h...

AI Technical Summary

Problems solved by technology

Compared with the subjective auscultation method, many scholars have paid attention to the computer-aided analysis of lung sound signals, such as using the Mel frequency cepstral coefficient that characterizes the auditory characteristics of the human ear as the acoustic feature, combined with the Gaussian method based on maximum likelihood estimation. The hybrid model completes the identification of abnormal lung sounds, etc., but the training feature value used in most methods is relatively single, and the function of the adopted model has not been extended to the fine classification of lung sounds, so there are still certain limitations

Images