Feature Analysis of Heart Sound Signal Based on Improved Hilbert-Huang Transform

In order to analyse the feature of heart sounds accurately and effectively, this paper presents a feature analysis approach of heart sound based on Hilbert-Huang Transform(HHT)after analysing a lot of heart sounds in time-frequency domain.The availability of the proposed method is proved to valid through the Empirical Mode Decomposition(EMD)for a typical vibration signal.The time-frequency spectrum and marginal spectrum of heart sound is obtained by Hilbert spectrum analysis of a standard heart sound signal.The results show that this method can characterize various heart sounds in time-frequency domain, and establishes the basis for the classification and recognition of heart sound.