[1]甘永进,赵 地,陈 辉,等.基于脉搏波特征参数的无创血红蛋白检测研究[J].燕山大学学报,2020,44(2):150-156.[doi:10.3969/j.issn.1007-791X.2020.02.006]
 GAN Yongjin,ZHAO Di,CHEN Hui,et al.Study of non-invasive hemoglobin concentration monitor based on characteristic parameters of pulse wave[J].Journal of YanShan University,2020,44(2):150-156.[doi:10.3969/j.issn.1007-791X.2020.02.006]
点击复制

基于脉搏波特征参数的无创血红蛋白检测研究
分享到:

《燕山大学学报》[ISSN:1007-791X/CN:13-1219/N]

卷:
44
期数:
2020年第2期
页码:
150-156
栏目:
信息与计算机技术
出版日期:
2020-03-31

文章信息/Info

Title:
Study of non-invasive hemoglobin concentration monitor based on characteristic parameters of pulse wave
文章编号:
1007-791X(2020)02-0150-07
作者:
甘永进1赵 地1陈 辉2李 琼1郑金存1*
1. 玉林师范学院 物理与电信工程学院,广西 玉林 537000;
2. 玉林师范学院 体育健康学院,广西 玉林 537000
Author(s):
GAN Yongjin1 ZHAO Di1CHEN Hui2 LI Qiong1 ZHENG Jincun1
1.School of Physics and Telecommunication Engineering,Yulin Normal University,Yulin,Guangxi 537000,China;
2.School of Physical Education&Health ,Yulin Normal University,Yulin,Guangxi 537000,China
关键词:
血红蛋白光电容积脉搏波特征参数特征子集支持向量回归
Keywords:
hemoglobin photoplethysmography characteristic parameter feature subset support vector regression
分类号:
R318;TP181
DOI:
10.3969/j.issn.1007-791X.2020.02.006
文献标志码:
A
摘要:
因传统血红蛋白检测方法对人体有创伤,需要专门的仪器且耗时长,基于此,提出一种基于光电容积脉搏波特征参数的无创血红蛋白检测方法。通过设计脉搏波采集系统采集指尖脉搏信号,再由EEMD结合形态学滤波的方法对原始脉搏波进行滤波处理,对降噪后的脉搏信号进行时域特征、频域特征以及形态特征的提取,并由皮尔森系数及PCA算法进行核心特征子集的构建,最后基于支持向量回归模型对人体血红蛋白进行预测。实验结果表明,该方法相关系数为0.76,对血红蛋白的检测具有一定的可靠性。
Abstract:
Traditional detection method of hemoglobin is invasive and needs special equipment with long detection time.To solve this problem,a non-invasive detection method of hemoglobin is proposed based on characteristic parameters of photoplethysmography.The acquisition system is designed to collect the finger photoplethysmography,and then the original photoplethysmography signal is filtered by EEMD and morphological filters.Next the time domain characteristics,frequency domain characteristics and morphological characters are extracted,then the core feature subset is built by Pearson coefficient and PCA,finally the prediction model to hemoglobin is designed based on support vector regression.The results show that the correlation coefficient between predicted value and true value is 0.76,the method has certain reliability to hemoglobin detection.

相似文献/References:

[1]甘永进,莫沛,陈时东,等.基于经验模态分解和形态滤波的血压测量研究[J].燕山大学学报,2019,43(1):048.[doi:10.3969/j.issn.1007-791X.2019.01.007]
 GAN Yongjin,MO Pei,CHEN Shidong,et al.Study on blood pressure measurement based on EMD and morphological filtering[J].Journal of YanShan University,2019,43(2):048.[doi:10.3969/j.issn.1007-791X.2019.01.007]

备注/Memo

备注/Memo:
收稿日期:2019-01-02        责任编辑:孙峰
基金项目:广西中青年教师能力提升项目(2019KY0585,2018KY0469);广西高校复杂系统优化与大数据处理重点实验室开放基金(2017CSOBDP0304);玉林师范学院校级科研项目(2019YJKY07)
作者简介:甘永进(1990-),男,广西贵港人,硕士,讲师,主要研究方向为生物医学信号检测与处理;*通信作者:郑金存(1979-),男,广西桂林人,硕士,副教授,主要研究方向为生物医学信号检测与处理,Email:fangxin_112@163.com
更新日期/Last Update: 2020-04-22