|本期目录/Table of Contents|

[1]陈真诚,孟凡涛,吴贤亮,等.基于双波长的无创血红蛋白浓度监测仪的研制*[J].生物医学工程研究,2018,03:309-314.
 CHEN Zhencheng,MENG Fantao,WU Xianliang,et al.Development of a non-invasive hemoglobin concentration monitor based on dual wavelength[J].Journal of Biomedical Engineering Research,2018,03:309-314.
点击复制

基于双波长的无创血红蛋白浓度监测仪的研制*(PDF)

《生物医学工程研究》[ISSN:1006-6977/CN:61-1281/TN]

期数:
2018年03期
页码:
309-314
栏目:
出版日期:
2018-09-25

文章信息/Info

Title:
Development of a non-invasive hemoglobin concentration monitor based on dual wavelength
文章编号:
1672-6278 (2018)03-0309-06
作者:
陈真诚1孟凡涛2吴贤亮2朱健铭13△
1.桂林电子科技大学生命与环境科学学院,广西 桂林 541004;2.桂林电子科技大学电子工程与自动化学院,广西 桂林 541004;3.广西信息科学实验中心,广西 桂林 541004
Author(s):
CHEN Zhencheng1 MENG Fantao2 WU Xianliang2 ZHU Jianming13
1. School of Life and Environmental Science, Guilin University of Electronic Technology, Guilin 541004, China;2.School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin 541004;3. Guangxi Information Science Experimental Center, Guilin 541004
关键词:
血红蛋白双波长ReliefFPCA希尔伯特-黄变换
Keywords:
Hemoglobin Dual-wavelength ReliefFPrinciple component analysisHilbert-Huang transform
分类号:
R318
DOI:
10.19529/j.cnki.1672-6278.2018.03.13
文献标识码:
A
摘要:
设计一款双波长无创血红蛋白浓度监测仪,可实时监测人体血红蛋白浓度。总体设计分为软硬件设计及算法研究。软硬件设计采用STM32F407作为主控芯片,选择MAX30100作为传感器,使用LCD液晶屏显示实时波形,使用SD卡进行数据存储。算法研究主要采用希尔伯特黄变换(HHT)对脉搏波进行滤波处理,采用PCA算法和RELIEF算法相结合对提取的27个时域特征参数筛选筛选出12个特征参数,利用PLS建立血红蛋白模型。本次研究中,选择响应速度快、精度高的艾康生物技术公司生产的Mission HB便携式血红蛋白分析仪作为对照仪器。同时,随机选择31名志愿者在相同的实验条件下进行验证实验,对31组实验数据进行分析,得到相关系数为0.728,均方差为0.9416 g/dL。结果表明,本研究建立的双波长血红蛋白检测模型对血红蛋白浓度检测提供了一定的研究依据,对临床研究具有重要的意义。
Abstract:
To design noninvasive hemoglobin concentration detector with dual-wavelength and it can be used to monitor hemoglobin concentration in real time. The design was constitute of two parts, which were overall hardware,software design and algorithm research. It used STM32F407 as its main control chip, selected MAX30100 as sensor, used a LCD screen showing real-time wave, and adopted by the SD card to store the data. The algorithm mainly used the Hilbert transform (HHT) to filter the pulse wave. The ReliefF algorithm combined with PCA was used to screen out 12 feature parameters from the 27 extracted feature parameters. Finally, PLS was used to build a hemoglobin model. The Mission Hb hemoglobin analyzer produced by the Aiken Biotechnology company which responded quickly and with high precision, chose the instrument as a control instrument. A total of 31 volunteers were selected randomly to perform validation experiments under the same experimental conditions. The experimental data of 31 groups were analyzed and the correlation coefficient was 0.728, with a mean square error of 0.9416 g/dL. The comparative result shows that the two-wavelength hemoglobin detection model established in this study provides a certain basis for the detection of hemoglobin concentration and is of great significance to clinical research.

参考文献/References

备注/Memo

备注/Memo:
(收稿日期:2017-12-22) 广西自然科学基金资助项目(2016GXNSFBA380145);广西自动检测技术与仪器重点实验室主任基金资助项目(YQ17118);2015年广西信息科学实验中心一般项目(YB1513)。△通信作者Email:zjmcsu@126.com
更新日期/Last Update: 2018-09-30