基于人工神经网络及小波分析的心音诊断方法
|
摘要
由于传统的心音听诊就是凭医生的经验用听觉分析心音信号,不能满足医学上所要求的高精确度性能而且听诊技能要花多年时间才能掌握,针对这些弊端本文提出了一种新的心音诊断方法。它对电子听诊器录制的心音数据,经过去噪预处理后用小波变换进行分析并提取特征值,再将选取的特征值输入到前馈型神经网络进行训练和识别。实验中我们用节点数分别为9,5,5的BP神经网络能成功识别出主动脉关闭不全,主动脉狭窄,二尖瓣关闭不全,二尖瓣狭窄,和正常心音五类心音,能为相应心脏疾病的诊断提供有力的依据,为临床应用提供有效的分析手段。
Heart auscultation with the bare ear and the stethoscope can not satisfy the high precision in medicine and forming a diag- nosis based on heart sounds is a skill that can take years to acquire. So this paper presents a diagnosis method on heart ausculta- tion. A library of heart sound files, recorded via an electronic stethoscope are used, features from these samples are extracted using discrete wavelet transform and the classification is trained and carried out by using a feed forward neural network. We collected sound samples of five categories, they are aortic regurgitation, aortic stenosis, mitral regurgitation, mitral stenosis and normal heard sound.The BP can regonise them succesfully. It can make up the shortage of heart auscultation and save the time to grasp the diag- nosis skill for doctors.
Heart auscultation with the bare ear and the stethoscope can not satisfy the high precision in medicine and forming a diag- nosis based on heart sounds is a skill that can take years to acquire. So this paper presents a diagnosis method on heart ausculta- tion. A library of heart sound files, recorded via an electronic stethoscope are used, features from these samples are extracted using discrete wavelet transform and the classification is trained and carried out by using a feed forward neural network. We collected sound samples of five categories, they are aortic regurgitation, aortic stenosis, mitral regurgitation, mitral stenosis and normal heard sound.The BP can regonise them succesfully. It can make up the shortage of heart auscultation and save the time to grasp the diag- nosis skill for doctors.
引文
[1]郑治真沈萍等.小波变换及MATLAB工具得应用.北京:地震出版社,2001..
[2]Huiying Liang,Iiro artimo.“A heart sound feature extraction al-gorithm based on wavelet decomposition and reconstructin,”IEEE,vol.20,no,3,pp.1539-1541,1998..
[3]Zhou Shiyong,Cao Zehan.“The knowledge-based signal analy-sis for a heart sound information system,”IEEE,vol.20,no.3,1998,pp.1622-1624,1998..
[4]李勇,高小榕,郭爱雯.基于连续小波变换得心音信号时频分析.清华大学学报2001第3期77-81
[5]谷云辉,刘亚斌.基于自动测试系统的故障诊断方法研究.[J]微计算机信息2005第19期146-148
[2]Huiying Liang,Iiro artimo.“A heart sound feature extraction al-gorithm based on wavelet decomposition and reconstructin,”IEEE,vol.20,no,3,pp.1539-1541,1998..
[3]Zhou Shiyong,Cao Zehan.“The knowledge-based signal analy-sis for a heart sound information system,”IEEE,vol.20,no.3,1998,pp.1622-1624,1998..
[4]李勇,高小榕,郭爱雯.基于连续小波变换得心音信号时频分析.清华大学学报2001第3期77-81
[5]谷云辉,刘亚斌.基于自动测试系统的故障诊断方法研究.[J]微计算机信息2005第19期146-148
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心