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 ›› 2019, Vol. 45 ›› Issue (11): 287-297. doi: 10.19678/j.issn.1000-3428.0052471

• 开发研究与工程应用 • 上一篇    下一篇

基于小波模极大值的脉搏信号特征点识别方法

傅之越1, 张睿1, 李福凤2   

  1. 1. 复旦大学 软件学院, 上海 201203;
    2. 上海中医药大学 基础医学院, 上海 201203
  • 收稿日期:2018-08-23 修回日期:2018-11-05 发布日期:2018-11-14
  • 作者简介:傅之越(1993-),男,硕士研究生,主研方向为模式识别、媒体计算;张睿,工程师、博士;李福凤,副主任医师、博士。
  • 基金资助:
    国家重点研发计划"中医药现代化研究重点专项"(2018YFC1707602);国家自然科学基金(81774205)。

Feature Point Recognition Method of Pulse Signal Based on Wavelet Modulus Maxima

FU Zhiyue1, ZHANG Rui1, LI Fufeng2   

  1. 1. Software School, Fudan University, Shanghai 201203, China;
    2. School of Basic Medical Science, Shanghai University of Traditional Chinese Medicine, Shanghai 201203, China
  • Received:2018-08-23 Revised:2018-11-05 Published:2018-11-14

摘要: 传统的脉搏信号时域特征点识别方法未考虑脉搏形态的多样性,缺乏与脉搏波形成机制之间的联系,从而限制了其识别准确性。为此,引入小波变换模极大值曲线及其奇异点检测理论,结合脉搏波形成机制和脉搏特征点释义,提出一种脉搏时域特征点识别方法。运用小波变换模极大值曲线检测脉搏信号中的奇异点,根据奇异点的性质与位置关系,确定各时域特征点所在的位置范围,利用差分法确定各个时域特征点的位置。实验结果表明,该方法不仅能避免脉搏频率不稳定性对特征点识别的干扰,而且能适应脉搏形态的多样性,其时域特征点识别准确率优于滑动窗口法、香农包络线法以及经验划分法。

关键词: 脉搏信号, 时域特征点, 小波模极大值, 上升支, 下降支, 奇异点检测

Abstract: The traditional pulse signal time domain feature point recognition method does not consider the diversity of pulse morphology,and lacks the connection with the pulse wave formation mechanism,thus limiting its recognition accuracy.To this end,the wavelet transform modulus maxima curve and its singularity detection theory are introduced.Combined the pulse wave formation mechanism with the pulse feature point interpretation,a pulse time domain feature point recognition method is proposed.The wavelet transform modulus maxima curve is used to detect the singularities in the pulse signal.According to the property and position relationship of the singularities,the position range of each time domain feature point is determined.The difference method is used to determine the position of each time domain feature point.Experimental results show that the proposed method can not only avoid the interference of pulse frequency instability on feature point recognition,but also adapt to the diversity of pulse morphology.The recognition accuracy of time domain feature points is better than sliding window method,Shannon envelope method and empirical division method.

Key words: pulse signal, time domain feature point, wavelet modulus maxima, ascending branch, descending branch, singularity detection

中图分类号: