RESUMO
Heart sounds are highly valuable to the clinical diagnoses of most cardiovascular diseases, so the analysis of phonocardiographic signals is helpful to diagnosing cardiovascular diseases clinically. Phonocardiographic signals are non-stable, so it is necessary to choose appropriate method in time-frequency analysis. The traditional method such as Fourier Transform is dissatisfactory. Continuous Wavelet Transform (CWT) and Matching (MPM) Pursuit Method are both effective methods. They can be used to extract and cluster the characteristics of the signals. By analysis and comparison, the two methods showed the advantages over traditional methods. Additionally, their respective merits and demerits are indicated.
Assuntos
Humanos , Algoritmos , Análise de Fourier , Ruídos Cardíacos , Fonocardiografia , Processamento de Sinais Assistido por ComputadorRESUMO
Independent component analysis (ICA) is a novel method developed in recent years for Blind Source Separation. In this paper, the phonocardiogram (PCG) was separated into three components by applying ICA. The basic principle of ICA was introduced in this paper. A fast and robust fixed-point algorithm for ICA was used to analyze PCG signals in this study. The experiments showed that ICA could separate the components of heart sounds from PCG signals successfully.