生物医学  >> Vol. 9 No. 1 (January 2019)

基于CEEMDAN样本熵的心音信号特征提取及识别研究
Feature Extraction and Recognition of Heart Sound Signal Based on CEEMDAN Sample Entropy

DOI: 10.12677/HJBM.2019.91001, PDF, 下载: 513  浏览: 1,465  国家自然科学基金支持

作者: 肖 苗, 常 俊, 王威廉*:云南大学信息学院,云南 昆明;潘家华, 杨宏波:云南省阜外心血管病医院,云南 昆明

关键词: 自适应噪声的完备经验模态分解样本熵心音先心病因子分解机 CEEMDAN (Complete Ensemble Empirical Mode Decomposition with Adaptive Noise) Sample Entropy Heart Sound CHD (Congenital Heart Disease) Factorization Machines (FM)

摘要: 针对心音信号的非平稳特性和易被噪声干扰的特点,本文提出一种基于自适应噪声的完备经验模态分解(CEEMDAN)与IMF样本熵结合的特征提取方法。将信号进行CEEMDAN自适应分解为若干个IMF分量,并计算各阶IMF分量的样本熵作为特征向量。在此基础上提出一种基于因子分解机(Factorization Machines, FM)的推荐模型,能更好的处理稀疏大数据的缺点,较好的解决了样本熵的稀疏性。为了验证该模型的优劣,进行了AUC曲线分析。通过对600例先心病病例心音和600例正常心音实验数据分析,证明该方法能够改善信号特征提取的效果,对先心病心音类型上的判断表现出较高的识别率。
Abstract: Due to the nonstationary characteristics of heart sound signal which was often disturbed by noise, a feature extraction method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) with IMF sample entropy was proposed in this work. The heart sound signals were adaptively decomposed into several IMF components by using CEEDDAN, and the sample entropy of each order IMF component was calculated as the feature vector. A recommendation model based on Factorization Machines (FM) was proposed, which can deal with the disadvantages of sparse big data and solve the sparsity of sample entropy better. In order to verify the pros and cons of the model, AUC curve analysis was performed. 600 heart sounds of congenital heart disease and 600 normal heart sounds were analyzed. It is proved that the method can improve the signal feature extraction and show a higher recognition rate for the heart sound of congenital heart disease.

文章引用: 肖苗, 常俊, 潘家华, 杨宏波, 王威廉. 基于CEEMDAN样本熵的心音信号特征提取及识别研究[J]. 生物医学, 2019, 9(1): 1-9. https://doi.org/10.12677/HJBM.2019.91001

参考文献

[1] 雍希. 基于EMD及SVD的心音信号提取方法研究[D]: [硕士学位论文]. 重庆: 重庆大学, 2016.
[2] Wu, Z.H. and Huang, N.E. (2009) Ensemble Empirical Mode Decomposition: A Noise-Assisted Data Analysis Method. Advances in Adaptive Data Analysis, 1, 1-41.
https://doi.org/10.1142/S1793536909000047
[3] Torres, M.E., Colominas, M.A., Schlotthauer, G., et al. (2011) A Complete Ensemble Empiric-Al Mode Decomposition with Adaptive Noise. IEEE International Conference on Acoustics, Speech and Signal Processing, 4144-4147.
[4] Richman, J.S. and Moorman, J.R. (2000) Physiological Time-Series Analysis Using Approximate Entropy and Sample Entropy. AJP Heart and Circulatory Physiology, 278, H2039-H2049.
[5] 喻飞, 赵志勇, 魏波. 基于差分进化的因子分解机算法[J]. 计算机科学, 2016(9): 269-273.
[6] 谢志谦, 孙虎儿, 刘乐, 等. 基于CEEMD-AN样本熵与SVM的滚动轴承故障诊断[J]. 组合机床与自动化加工技术, 2017(3): 96-100.
[7] 李余兴, 李亚安, 陈晓, 等. 一种基于样本熵与EEMD的舰船辐射噪声特征提取方法[J]. 水下无人系统学报, 2018(1): 28-34.
[8] 丁晨莉, 马彦韬, 黄强民, 等. 利用样本熵分析针刺肌筋膜疼痛触发点的疗效[J]. 针刺研究, 2018(2): 127-132.
[9] 刘荣海, 豆龙江, 万书亭, 等. 基于EEMD样本熵和支持向量机的高压断路器故障诊断[J]. 华北电力大学学报(自然科学版), 2018(2): 82-88.
[10] 胡显能, 蔡改贫, 罗小燕, 等. 基于CEEMDAN和多尺度排列熵的球磨机负荷识别方法[J]. 噪声与振动控制, 2018(3): 146-151.
[11] 任国春, 赵永东. 基于EEMD样本熵与LS-SVM的行星齿轮箱故障诊断[J]. 山东工业技术, 2018(3): 214-215.
[12] 李振璧, 张坤, 姜媛媛, 等. 基于变分模态分解与近似熵的输电线路两相接地故障诊断[J]. 科学技术与工程, 2018(5): 70-75.