Heart sound signal classification method based on convolutional recurrent neural network

Abstract

The invention discloses a heart sound signal classification method based on a convolutional recurrent neural network. The method comprises the following steps: performing noise processing on heart sound data; extracting heart sound characteristics of the heart sound signals; standardizing the data; constructing a convolutional recurrent neural network model; training the constructed neural networkby using the training sample data characteristics, and storing the trained network structure and parameters; and testing the test sample data by using the trained model parameters to obtain a final classification and identification result. According to the invention, the system complexity is reduced; the extracted heart sound characteristics do not need to segment heart sound signals; according to the heart sound signal classification method based on the convolutional neural network, the convolutional neural network and the recurrent neural network are connected in series, a deep learning model with the processing advantages of the convolutional neural network and the recurrent neural network is provided, better expressive force is provided for heart sound signal classification, and an effective and convenient tool is provided for detection of normal and abnormal heart sound signals.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, and in particular relates to a heart sound signal classification method based on a convolutional cyclic neural network. Background technique [0002] Heart sounds, as a physical sign reflecting the human heart activity and cardiovascular function, can be easily heard by the human ear through devices such as stethoscopes. As a non-invasive diagnostic method, heart sound examination (auscultation) has become an important criterion for clinical diagnosis of cardiovascular diseases and related diseases, and almost every hospital will have this routine examination. Compared with electrocardiogram, apical pulse diagram, carotid pulse diagram, etc., the diagnostic method of phonocardiogram obtained by auscultation of heart sounds has great advantages in terms of easy operation, low cost, and portability, but it also has a certain degree of subjectivity and One-sided, it is closely related t...

AI Technical Summary

Problems solved by technology

[0003] For special non-stationary periodic signals such as heart sounds, the purpose of this invention is to solve the problems of traditional heart sound analysis relying on doctor's experience and low accuracy, and propose a method for classifying heart sound signals based on convolutional cyclic neural network. Quantitative analysis of heart sound signals makes the results of heart sound auscultation more accurate, and provides a simple, convenient, cheap, effective, and predictive deep learning method for heart sound recognition and diagnosis

Images