摘要
从心音图中准确提取第一心音和第二心音的时域特性,是一个巨大的挑战,特别是在心脏出现病理的情况下。一个检测心脏疾病的系统,需要对心音信号的心动周期进行适当的边界估计。边界估计算法能够从心音图中给出准确的第一、第二心音的边界。提出一种新颖的边界估计算法,采用生物域特征,大大减少计算的时间和复杂度,而且更加准确。在此算法基础上,对50例心音样本进行分段识别,准确率达到96.30%,为下一步心音分析与诊断奠定基础。
Determining the exact timing of the cardiac events by the first and second heart sounds from the phonocardiogram（PCG） signal, represents a great challenge, especially in pathological cases. A system that allows the detection of heart diseases, is needed a properly boundary estimated cardiac cycles of heart sound signal. Boundary estimation algorithm gives the exact boundary of the S1 and S2 of PCG signal. Proposes a novel method of boundary estimation algorithm that extensively utilizes biomedical domain features for reduction of time and computational complexities and is more accurate. The heart sound of 50 samples are recognized with the accuracy of 96.30%, lays the foundation of further heart sound analysis and diagnosis.
出处
《现代计算机》
2009年第11期10-13,共4页
Modern Computer
基金
山东省自然基金(No.y2006G03
No.y2007G14
No.2006Gg3204005)
关键词
第一心音
第二心音
边界估计
分段算法
First Heart Sound
Second Heart Sound
Boundary Estimation
Segmentation Algoritym
