Multi-channel cardiopulmonary sound anomaly recognition system and device based on low-rank tensor learning

Abstract

The invention discloses a multi-channel cardiopulmonary sound anomaly recognition system and device based on low-rank tensor learning. The method comprises the following steps: acquiring a cardiopulmonary sound signal of a human body in an array through a sound pickup consisting of three sound pickups, amplifying the cardiopulmonary sound signal by using a gain regulator, obtaining the cardiopulmonary sound signal with a high signal-to-noise ratio through a filter, converting the cardiopulmonary sound signal into a digital signal through an ADC module, and transmitting the digital signal to asingle chip microcomputer, wherein single-chip microcomputer carries out short-time Fourier transform processing on the mixed cardiopulmonary sound signals collected by the three channels, a window function adopted by short-time Fourier transform is a Hamming window, and after short-time Fourier transform is carried out on the signals of the three channels, three time-frequency spectrums are obtained; training a low-rank tensor classification model according to the acquired cardio-pulmonary sound tensor data and a given label to obtain pre-trained learning parameters; and when newly acquired auscultation data is given, predicting whether the cardiopulmonary sound data of the patient is abnormal or not by using the classification model. According to the invention, learning parameters can bereduced, and a small-sample cardiopulmonary sound anomaly identification task can be realized.

Description

technical field [0001] The invention relates to the field of intelligent electronic auscultation, in particular to a multi-channel heart and lung sound abnormality recognition system and device based on low-rank tensor learning. Background technique [0002] In recent years, the intelligent analysis of cardiopulmonary sounds has been developed in the time domain, frequency domain and power spectrum analysis to the current time-frequency analysis. Time-spectral analysis of heart and lung sounds has become an effective and popular method. In order to effectively identify abnormal heart and lung sound signals based on the time-spectrum of heart and lung sounds, research scientists have proposed many methods, including support vector machines (C.Sowmiya and P.Sumitra, "Analytical study of heart disease diagnosis using classification techniques , "2017 IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS), Srivilliputhur, ...

AI Technical Summary

Problems solved by technology

On the one hand, after simply vectorizing the time-spectrum, and then further using the above-mentioned method to detect anomalies, this simple method of vectorizing the time-spectrum will destroy the time and space structure of the data, so that its A better learning effect cannot be achieved; on the other hand, the large-scale learning parameters of the above-mentioned classifiers need to provide a large number of training samples, which does not meet the actual needs

Images