基于小波分析和神经网络的心音信号研究

针对传统的冠心病诊断方法具有不准性或有创性问题,积极广泛开展冠心病无损检测的研究,提高诊断准确性,为大众提供方便可行的检测手段是十分必要的。在分析冠状动脉堵塞与心音信号关系的基础上,研究心音信号的预处理,对心音信号进行去噪和定位分段;利用ARMA模型及功率谱估计对心音信号进行分析研究,提取冠心病病理特征;通过神经网络对心音信号进行分类,实现冠心病的智能无损诊断。实验结果表明,采用上述方法进行冠心病无损诊断准确率达到85.1%,为临床上的冠心病的无损诊断提供了应用基础。

Study on Heart Sounds Signals Based on Wavelet Analysis and Neural Network

Traditional diagnostic methods of coronary heart disease have inaccuracy.And people who are detected by this method suffer a lot.Therefore,carrying out extensive non-destructive detecting method for coronary heart disease and providing the public with a means to facilitate the viable detection are very necessary.Research on phonocardiogram signal pre-processing was carried out based on the analysis of the relationship between coronary artery blockages and heart sound signals.And then the de-noise and the su...