作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2012, Vol. 38 ›› Issue (16): 174-177. doi: 10.3969/j.issn.1000-3428.2012.16.045

• 人工智能及识别技术 • 上一篇    下一篇

基于双门限的第一、第二心音自动识别方法

陈 洁,侯海良,罗良才,成 运   

  1. (湖南人文科技学院通信与控制工程系,湖南 娄底 417000)
  • 收稿日期:2011-10-08 修回日期:2011-12-06 出版日期:2012-08-20 发布日期:2012-08-17
  • 作者简介:陈 洁(1981-),女,讲师、硕士,主研方向:数字信号处理;侯海良,讲师、硕士;罗良才,教授;成 运,教授、博士后
  • 基金资助:
    湖南省自然科学基金资助项目(07JJ6116);湖南省科技基金资助项目(06SK3106);湖南省教育厅优秀青年基金资助项目(09B053)

Automatic Identification Method for the First and Second Heart Sound Based on Double-threshold

CHEN Jie, HOU Hai-liang, LUO Liang-cai, CHENG Yun   

  1. (Department of Communications & Control Engineering, Hunan Institute of Humanities, Science and Technology, Loudi 417000, China)
  • Received:2011-10-08 Revised:2011-12-06 Online:2012-08-20 Published:2012-08-17

摘要: 为提高心音检测算法对异常心音的识别率,提出一种基于双门限的第一心音(S1)和第二心音(S2)自动识别方法,通过海明窗进行滤波预处理,采用改进型希尔伯特-黄变换提取心音包络,利用双门限法对心音进行分段,使用临床知识对S1和S2进行自动识别。实验结果表明,该方法能够准确识别正常心音和异常心音中的S1和S2。

关键词: 希尔伯特-黄变换, 心音包络, 经验模态分解, 端点效应, 双门限法, 分段

Abstract: Although most existing heart sound detection algorithms perform well in normal signals, they usually have no effect on abnormal signals. In this paper, an algorithm based on double-threshold method is proposed for robust detection of the first heart sound(S1) and second heart sound(S2). The original Heart Sounds Signal(HSS) is preprocessed by filter based on Hamming window. The envelope of heart sounds is extracted by improved Hilbert Huang Transform(HHT) and segmentation of heart sounds is realized by double-threshold method. The first and second heart sound are recognized automatically by clinic knowledge. Reliability of this proposed approach is confirmed through identification of S1 and S2 on several normal and abnormal heart sounds.

Key words: Hilbert Huang Transform(HHT), envelope of heart sound, Empirical Mode Decomposition(EMD), end effect, double-threshold method, segmentation

中图分类号: