Heart Sound Acquisition And Analysis Methods

Heart sound signal is one of the most primary physiological signals. Detection of heart sounds is an important method with judging the state of heart which has its own advantages that ECG can not replace. Heart sound can be used to diagnose of heart diseases. The phonocardiogram (PCG) records plenty of useful information that ear can not differentiate. Analysis of each parts of PCG will be helpful to diagnose the clinic heart diseases. Heart sound is a kind of non-stationary and complex signal, It is very difficult to analyze visually. With the rapid development in computer science and digital technology, A variety of methods are applied for the analysis of PCG signals, But these methods extract only limited information from the PCG signal. Now many specialists and scholars are trying to do many exploring research, By using a efficacious method and classify algorithm to study the heart sound.The PCG signal is non-stationary. In order to get a comprehensive understanding of the characteristic for the heart sound, it is necessary to analyze heart sound in time, frequency and time-frequency domain. Due to the interference, the heart sound signal is noised so that the preprocessing is necessary to remove the noises. After the preprocessing, the quality of signal is improved and can be used for further analysis.In this paper, the main contents of the study are listed below:1. Designed a simple,low-cost devices of acquisition heart sounds, combining collection and implementation of heart sound playback of software.2. In order to eliminate the noise of hear sounds, we proposed wavelet threshold denoising method, Which improved traditional threshold of function and made denoising results are very good and better flexibility.3. In order to get a more accurate time-domain characteristics, we through the EMD(empirical mode decomposition) algorithm for extraction the envelope of heart sounds. and show a sub-algorithm for heart sound steps and strategies. Taking into account the diversity and complexity of heart sound signal, we make experiments with many data collection as well as the actual experimental data, obtaining a high rate of right.4. HHT is introduced to study of heart sound signals and the methods of heart sound analysis and feature extraction are established base on HHT.5. The principle of SVM classification and idea of SVM multi-classification is introduced, and a classification of heart sounds is proposed based on SVM...