Non-negative matrix factorization-based heart and lung sound separation method and apparatus

Abstract

The invention discloses a non-negative matrix factorization-based heart and lung sound separation method. The method comprises the steps of firstly filtering a mixed signal of heart and lung sounds in a time domain to obtain a priori heart sound signal and a priori lung sound signal; secondly performing short-time Fourier transform and sparse non-negative matrix factorization on the priori heart sound signal and the priori lung sound signal; and finally obtaining a basis matrix of the mixed signal. The sparse non-negative matrix factorization process is equivalent to a learning process of the basis matrix, and has a clustering effect; the basis matrix can be mined effectively from the priori heart sound signal and the priori lung sound signal; and a heart sound signal and a lung sound signal are accurately separated from the mixed signal of the heart and lung sounds in the time domain according to the basis matrix in the subsequent steps. The invention furthermore discloses a non-negative matrix factorization-based heart and lung sound separation apparatus, which has the abovementioned beneficial effects.

Description

technical field [0001] The invention relates to the field of audio frequency separation, in particular to a method and device for heart-lung sound separation based on non-negative matrix decomposition. Background technique [0002] Due to the continuous improvement of modern living standards, people's health problems have become increasingly prominent, among which the morbidity and mortality of cardiovascular diseases and other heart organ diseases are increasing. At the same time, with the increasing air pollution in recent years, the incidence of lung diseases such as asthma, chronic obstructive pulmonary disease, and pneumonia is also increasing. The health problems of the human cardiopulmonary system have attracted the attention of the medical community today. Accurate diagnosis of the cardiopulmonary system is an effective way to ensure early recovery of patients. [0003] Heart sound, that is, the rhythm of the human heart organ is the sound, which contains physiologi...

AI Technical Summary

Problems solved by technology

The above-mentioned fully supervised or semi-supervised non-negative matrix factorization method requires very pure prior knowledge of heart sounds or lung sounds in the implementation process, and has a high dependence on manual operation in the clinical application process.

Images