基于EMD和MFCC的舒张期心杂音的分类识别

发布时间：2018-10-11 17:41

【摘要】：心音信号是一种具有非线性和非平稳特性的振动信号,基于线性时变或时不变模型的特征提取方法势必会忽略信号的一些内在信息,为了更好的反映心音的本质特征,提出了一种经验模式分解(Empirical Mode Decomposition,EMD)结合Mel频率倒谱系数(Mel-Frequency Cepstrum Coefficient,MFCC)的舒张期心杂音的分类识别方法。心音信号经EMD分解得到有限个固有模态函数(Intrinsic Mode Function,IMF),利用互相关系数准则筛选出主IMF分量,分别提取主IMF分量的MFCC、MFCC的一阶差分系数和Delta值,以此作为隐马尔科夫模型的输入向量,实现对临床采集的正常心音和2类舒张期心杂音分类识别,实验结果表明,该方法能有效的识别心音。
[Abstract]:Heart sound signal is a kind of vibration signal with nonlinear and non-stationary characteristics. The feature extraction method based on linear time-varying or time-invariant model is bound to ignore some internal information of the signal, in order to better reflect the essential characteristics of heart sound. An empirical mode decomposition (Empirical Mode Decomposition,EMD) method combined with Mel frequency cepstrum coefficient (Mel-Frequency Cepstrum Coefficient,MFCC) is proposed for the classification of diastolic heart murmur. The heart sound signal is decomposed by EMD to obtain finite intrinsic mode function (Intrinsic Mode Function,IMF). The main IMF component is screened out by using the correlation number criterion, and the first order difference coefficient and Delta value of the main IMF component are extracted respectively, which is used as the input vector of the hidden Markov model. The classification and recognition of normal heart sounds and two kinds of diastolic murmur are realized. The experimental results show that this method can recognize heart sounds effectively.
【作者单位】：重庆大学生物工程学院重庆市医疗电子技术工程研究中心;
【基金】：国家自然科学基金(31570003)
【分类号】：R540.4;TN912.3

【相似文献】