期刊文献+

基于PCA和HMM的心音自动识别系统 被引量:3

Heart Sounds Automatic Recognition System Based on PCA and HMM
下载PDF
导出
摘要 针对信号识别率高低由识别模型及特征参数决定的特点,提出融合K均值聚类的多观察序列的Baum-Welch参数重估算法,用于训练隐马尔科夫模型(HMM),通过主分量分析(PCA)对梅尔频率倒谱系数进行变换,并设计与实现一套基于PCA和HMM的心音自动识别系统。实验结果表明,该系统对6类常见心音的平均识别率达到83.3%,性能优于其他心音识别系统。 According to the signal recognition rate decided by recognition model and the characteristic parameters, this paper puts forward the fusion K-means clustering of the observed sequence Baum-Welch parameters estimation algorithm to train Hidden Markov ModeI(HMM), the Principal Component Analysis(PCA) is adopted to transform Mel Frequency Cepstrum Coefficient(MFCC) features. A heart sounds signal automatic diagnosis system is designed based on PCA and HMM. Experimental results show that the average recognition rate of 6 common elasse's heart sounds reaches 83.3%, the performance is better than other heart sound recognition systems.
出处 《计算机工程》 CAS CSCD 2012年第20期148-151,共4页 Computer Engineering
基金 广西自然科学基金资助项目(A053232) 广西研究生创新基金资助项目(2011105950810M16) 桂林电子科技大学基金资助项目(UF11012Y)
关键词 梅尔频率倒谱系数 主分量分析 隐马尔科夫模型 K均值聚类 Baum-Welch算法 心音识别 Mel Frequency Cepstrum Coefflcient(MFCC) Principal Component Analysis(PCA) Hidden Markov ModeI(HMM) K-means clustering Baum-Welch algorithm heart sounds recognition
  • 相关文献

参考文献8

  • 1Wang Ping, Lim Chu-Sing, Chauhan S, et al. A Computer Aided MFCC Based HMM System for Automatic Ausculation[J]. Computers in Biology and Medicine, 2008, 38(2): 221-233.
  • 2Maglogiannis I, Loukis E, Zafiropoulos E, et al. Support Vector Machine-based Identification of Heart Valve Diseases Using Heart Sounds[J]. Computer Methods and Programs in Biomedicine, 2009, 95(1): 47-61.
  • 3陈燕龙,钟碧良.基于HMM和微粒群优化算法的表情识别[J].计算机工程,2008,34(13):190-192. 被引量:1
  • 4郭军涛,林森财,田晓东,陈基明.心音信号的检测与处理[J].现代仪器,2008,14(2):36-38. 被引量:7
  • 5Djebbari A, Bereksi R F. Short-time Fourier Transform Analysis of the Phonocardiogram Signal[C] //Proc. of the 7th IEEE Inter- national Conference on Electronics, Circuits and Systems. Kaslik, Lebanon: [s. n.] , 2000: 844-847.
  • 6邵央,刘丙哲,李宗葛.基于MFCC和加权矢量量化的说话人识别系统[J].计算机工程与应用,2002,38(5):127-128. 被引量:34
  • 7董火明,高隽,胡良梅,董文雯.基于主分量分析的形状特征提取及识别研究[J].合肥工业大学学报(自然科学版),2003,26(2):176-179. 被引量:25
  • 8Li Xiaolin, Parizeau M, Plamondon R. Training Hidden Markov Models with Multiple Observations: A Combinatorial Method[J]. IEEE Trans. on PAMI, 2000, 22(4): 371-377.

二级参考文献25

共引文献63

同被引文献21

引证文献3

二级引证文献10

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部