计算机工程 ›› 2012, Vol. 38 ›› Issue (20): 148-151.doi: 10.3969/j.issn.1000-3428.2012.20.038

• 人工智能及识别技术 • 上一篇    下一篇

基于PCA和HMM的心音自动识别系统

王晓燕,曾庆宁,粟秀尹   

  1. (桂林电子科技大学信息与通信学院,广西 桂林 541004)
  • 收稿日期:2011-12-12 修回日期:2012-02-26 出版日期:2012-10-20 发布日期:2012-10-17
  • 作者简介:王晓燕(1985-),女,硕士研究生,主研方向:医学信号处理;曾庆宁,教授;粟秀尹,硕士研究生
  • 基金项目:
    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(UF 11012Y)

Heart Sounds Automatic Recognition System Based on PCA and HMM

WANG Xiao-yan, ZENG Qing-ning, SU Xiu-yin   

  1. (College of Information and Communications, Guilin University of Electronic Technology, Guilin 541004, China)
  • Received:2011-12-12 Revised:2012-02-26 Online:2012-10-20 Published:2012-10-17

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。

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

Abstract: 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 Model(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 classe’s heart sounds reaches 83.3%, the performance is better than other heart sound recognition systems.

Key words: Mel Frequency Cepstrum Coefficient(MFCC), Principal Component Analysis(PCA), Hidden Markov Model(HMM), K-means clustering, Baum-Welch algorithm, heart sounds recognition

中图分类号: