【摘要】 在一些致命性心脏病的诊断中,心音听诊是最有效也是应用得最成功的手段之一。鉴于目前机械瓣的使用非常普遍,研究简单有效的机械瓣病变判别方法对于临床诊断来讲具有重要意义。运用希尔波特-黄变换(HHT),针对不同的机械瓣心音进行分析,并设计一种基于Hilbert边界谱特征的提取方法,结合线性判别分析(LDA),对不同的机械瓣心音进行分类。同时,与基于局部最优基特征的分类器分类结果进行比较。分析结果表明,机械瓣心音的各阶Hilbert边界谱具有非常明显不同的分布,基于HHT的分类器识别率达到了97.3%,较基于局部最优基特征分类器的识别率(91.3%)更高。对于人造机械瓣心音而言,HHT是一种有效的分析处理手段。更多还原

【Abstract】 Auscultation is a widely used efficient technique by cardiologists for detecting some deadly heart diseases.Since the mechanical prosthetic heart valves are widely used today,it is important to develop a simple and efficient method to detect abnormal mechanical valves.In this paper,Hilbert-Huang transform(HHT) was applied to analyze the heart sounds with different kinds of mechanical prosthetic valves.A Hilbert marginal spectral based feature extraction procedure was also developed.Combined with linear discriminant analysis(LDA),the extracted features were used to classify different kinds of heart sounds for mechanical prosthetic heart valves.Experimental results showed that the spectrum of different heart sounds were significantly different.The proposed classifier achieved a recognition rate of 97.3%,higher than the one based on local discriminant bases(91.3%).It is demonstrated that HHT is an efficient analyzing technique for artificial heart valve sounds.更多还原