基于HHT和PPA的心音分段算法研究

RESEARCH ON HHT AND PPA-BASED HEART SOUNDS SEGMENTATION ALGORITHM

心音是人体的一种重要的生理信号,它含有大量关于心脏病理状况的相关信息,反映了心脏及心血管结构及生理和病理信息。针对能否有效地提取第一心音(S1)、第二心音(S2),从而判断心脏是否病变,并且作为后续研究的基础,提出基于HHT和PPA的心音分段算法,包括首先利用希尔伯特-黄变换(HHT)进行心音包络的提取,然后利用中值滤波对包络进行平滑处理,最后通过峰逐层算法(PPA)来消除多余的低幅度峰值。通过对40例心音进行分段处理,可以对其中的39例进行正确分段。结果证明这种方法可以有效地提取心音信号的S1、S2,为后期的识别研究奠定了良好的基础。

Heart sounds is a kind of important physiological signals of human body,it contains a lot of relevant information about cardiac pathological conditions and reflects the heart and cardiovascular structures as well as the physiological and pathological information.For the problems of can or cannot effectively extract the first heart sound （S1 ）and the second heart sound （S2）so as to estimate whether there is the lesion in heart,which is the foundation of the follow-up study,we propose an HHT and PPA-based heart sounds segmentation algorithm, which includes three phases：first it uses Hilbert-Huang transform （HHT）for heart sound envelope extraction,and then it uses median filter to smooth the envelope,finally through the peak peeling algorithm （PPA）it eliminates the redundant low amplitude peaks.By segmentation processing on 40 cases of heart sounds,there are 39 cases can be properly segmented.Result shows that this method can effectively extract the heart sound signals S1 ,S2,which lays a good foundation for later recognition research.