Classification and identification method and device for cardiechema signals

Abstract

The invention provides a classification and identification method for cardiechema signals and a classification and identification device for cardiechema signals by applying the method. In the method, the likelihood of GMM template features and Mel-frequency cepstrum coefficients of the cardiechema signals to be detected is used as the matching standard to perform classification and identification, so the method has the advantages of few extracted parameters, simplified processes of feature extraction and calculation, strong anti-interference capacity and high accuracy and efficiency of the classification and identification. The classification and identification device for the cardiechema signals is designed by taking the method as the total idea, adopts a DSP processor as a processing core, and has a simple, exquisite, light and convenient structure, can be carried on for measurement, is a low-cost and non-invasive cardiechema detection device, and is helpful for discovering and treating cardiac diseases in time.

Description

Technical field [0001] The invention belongs to the technical field of intelligent control applications, and particularly relates to a heart sound signal classification and recognition method and a device thereof, which provide an effective tool for automatic classification of related heart diseases. Background technique [0002] Heart sounds contain a lot of physiological and pathological information about the heart. Before cardiovascular disease has developed enough to produce clinical and pathological changes, the murmurs and aberrations in heart sounds are of great significance to the diagnosis of heart valve disease and certain congenital heart diseases. Heart sound auscultation is an important way to check the integrity of the heart function. A professionally trained physician can use a stethoscope to roughly diagnose whether the patient has heart disease. However, heart auscultation is easily affected by the doctor’s experience and the level of auscultation. Restrictions,...

AI Technical Summary

Problems solved by technology

These research results have broadened the research ideas of heart sound classification, but these methods need to extract a variety of heart sound parameters as heart sound classification standards, and extracting too many heart sound parameters makes the extraction, calculation, and recognition processes cumbersome, and has to rely on complex structures and powerful computing functions. The computer system is used to perform the classification and processing of heart sound signals, not only the classification and recognition speed is relatively slow, but also the system is not easy to carry around

Images