Research on prediction model for hemoglobin concentration based on BP neural network

XU Cuimin; LI Shiyong; ZENG Ruosheng; CHEN Zhencheng

doi:10.13873/J.1000-9787(2020)08-0032-04

Chinese

您当前的位置：

首页 >

文章列表页 >

Research on prediction model for hemoglobin concentration based on BP neural network

更新时间：2025-09-11

- Research on prediction model for hemoglobin concentration based on BP neural network
- Issue 8, Pages: 32-35(2020)
- 作者机构：
  
  1. 桂林电子科技大学电子工程与自动化学院
  2. 桂林电子科技大学生命与环境科学学院
- 作者简介：
- 基金信息：
- DOI：10.13873/J.1000-9787(2020)08-0032-04
  CLC： R446.1;R556;TP183
- Published：2020
- 稿件说明：
移动端阅览
XU Cuimin, LI Shiyong, ZENG Ruosheng, et al. Research on prediction model for hemoglobin concentration based on BP neural network[J]. 2020, (8): 32-35.
DOI：

XU Cuimin, LI Shiyong, ZENG Ruosheng, et al. Research on prediction model for hemoglobin concentration based on BP neural network[J]. 2020, (8): 32-35. DOI： 10.13873/J.1000-9787(2020)08-0032-04.

摘要

为实现人体血红蛋白浓度的无创检测

建立了基于反向传播(BP)神经网络的血红蛋白浓度预测模型。采用MAX30102传感器与STM32F103芯片构成数据采集系统

采集人体指端光电容积脉搏波(PPG)数据。通过小波变换算法消除原始脉搏波信号中的基线漂移噪声

提取22个PPG时域特征参数与3个人体特征参数。结合Relief-PCA算法对这25个特征参数进行筛选

确定出10个关键特征参数作为输入值构建BP神经网络模型。一共采集115组数据

随机选择80组作为模型的训练集、35组为测试集。参考值为Misson HB血红蛋白分析仪测出的微创值。经过对比研究

其相关系数达到了0.88

均方误差为0.71 g/d L。研究表明

基于BP神经网络的血红蛋白浓度检测系统能够较好地对血红蛋白浓度进行测量。

Abstract

In order to achieve non-invasive detection of human hemoglobin concentration

a prediction model for hemoglobin concentration based on BP neural network is established. MAX30102 sensor and the chip STM32 F103 are used as data acquisition systems to collect the photoplethysmographic pulse wave data of the human fingertip.The baseline drift noise in the original pulse wave signal is eliminated by wavelet transform algorithm

and 22 PPG time domain feature parameters and 3 human body feature parameters are extracted. Combined with Relief-PCA algorithm

these 25 characteristic parameters were screened

and 10 key feature parameters are determined as input values to construct BP neural network model. A total of 115 sets of data are collected

80 sets are randomly selected as the training set of the model

and 35 sets are the test set. The reference value is the minimally invasive value measured by the Misson HB hemoglobin analyzer. After comparative study

the correlation coefficient reaches0. 88 and the mean square error is 0. 71 g/d L. Studies show that the hemoglobin concentration detection system based on BP neural network can better measure the hemoglobin concentration.

关键词

Keywords

references

Views

384

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Application of FCM and neural network in power load data correction

Application of modified SFLA-BP neural network in covering jamming signals identification

Magnetic flux leakage detection method by 3D Hall sensor array

Research on model for feature self-extracted blood pressure prediction based on deep learning

Short-term traffic flow prediction model based on self-variation fireworks algorithm

Related Author

ZHOU Zhiyi

LI Yalan

ZHANG Chunyan

PEI Tingting

SONG Jixiang

HAO Xiaohong

CHU Shupei

YANG Jie

Related Institution

College of Electrical Engineering and Information Engineering,Lanzhou University of Technology

College of Computer and Communication,Lanzhou University of Technology

Grid Technology Center,Power Science Research Institute of Gansu Electric Power Company

School of Communication and Information Engineering, Xi’an University of Posts and Telecommunications

Shandong Polytechnics

⁰