手机十三水作弊软件|十三水棋牌游戏赚钱
首页 > 论文 > 激光与光电子学进展 > 56卷 > 4期(pp:41701--1)

考虑多种因素的近红外光谱血糖预测模型对比

Comparison of Multi-Factor-Considered Blood Glucose Prediction Models by Near-Infrared Spectroscopy

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

以血糖浓度为例,采用将动态光谱提取数据和非测量组分影响因素一同纳入预测模型的方式来提高血糖测量系统中的精?#21462;?#36890;过支持向量算法建立血糖预测的模型,建模结果表明,考虑多因素模型的预测值优于未考虑非测量组分模型中的预测值。与后者相比,前者的相关系数达到0.9627,提高了14.23%; 均方根误差为0.13,减少了43.12%; 相对误差在10%范围内的样本数量增加8.33%。

Abstract

Taking the blood glucose concentration as an example, the accuracy of the blood glucose measurement system is improved by means of the simultaneous incorportation of the extraction data form dynamic spectra and the influencing factors of non-measured components into the prediction model. The blood glucose prediction model is established through the support vector machine algorithm. The modeling results show that the prediction value from the multi-factor-considered model is superior to that from the non-measurement-component-considered model. The correlation coefficient of the former is 0.9627, higher by 14.23% , the root mean square error is 0.13, reduced by 43.12%, and the number of samples with a relative error in the range of 10% is higher by 8.33%, compared with those of the latter.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:Q819

DOI:10.3788/lop56.041701

所属栏目:医用光学与生物技术

基金项目:?#26412;?#24066;自然科学基金(7172035)

收稿日期:2018-09-04

修改稿日期:2018-09-09

网络出版日期:2018-09-18

作者单位    点击查看

王晓飞:?#26412;?#20449;息科技大学仪器科学与光电工程学院, ?#26412;?100192
张欣怡:?#26412;?#20449;息科技大学仪器科学与光电工程学院, ?#26412;?100192
徐馨荷:?#26412;?#20449;息科技大学仪器科学与光电工程学院, ?#26412;?100192

联系人作者:王晓飞([email protected])

【1】Yang X, Ji Z, Yang L, et al. The principles and research status of noninvasive glucose detection based on near-infrared spectrum[J]. Journal of Biomedical Engineering, 2013, 30(1): 204-207.
杨星, 季忠, 杨力, 等. 基于近红外光谱法的无创血糖检测原理与研究现状[J]. 生物医学工程学杂志, 2013, 30(1): 204-207.

【2】Wang X F, Zhao W J. Measurement of multi-wavelength pulse oxygen saturation based on dynamic spectroscopy[J]. Spectroscopy and Spectral Analysis, 2014, 34(5): 1323-1326.
王晓飞, 赵文俊. 基于动态光谱法的多波长脉搏血氧饱?#25237;?#27979;量[J]. 光谱学与光谱分析, 2014, 34(5): 1323-1326.

【3】Zhang Y, Ni J S, Zhang Y Z, et al. Tissue intrinsic fluorescence spectrum recovery algorithm and its application in diabetes screening[J]. Chinese Journal of Lasers, 2018, 45(7): 0707001.
张洋, 倪?#35789;? 张元志, 等. 组织固有荧光光谱复原算法及其在糖尿病筛查中的应用研究[J]. 中国激光, 2018, 45(7): 0707001.

【4】Li D M, Jia S H. Application of BP artificial neural network in blood glucose prediction based on multi-spectrum[J]. Laser & Optoelectronics Progress, 2017, 54(3): 031703.
李东明, 贾书海. 基于多光谱应用BP人工神经网络预测血糖[J]. 激光与光电子学进展, 2017, 54(3): 031703.

【5】Sun K, Zhou H, Yang Y K, et al. Research advances in blood glucose monitoring system[J]. Chinese Journal of Lasers, 2018, 45(2): 0207003.
孙凯, 周华, 杨膺琨, 等. 血糖监测系统的研究进展[J]. 中国激光, 2018, 45(2): 0207003.

【6】Li G, Li Z, Wang X F, et al. Evolution of measure mode and proposition of “M+N” theory[J]. Journal of Beijing Information Science & Technology University, 2013, 28(2): 9-13.
李刚, 李哲, 王晓飞, 等. 测量模式的演进与“M+N”理论的提出[J]. ?#26412;?#20449;息科技大学学报(自然科学版), 2013, 28(2): 9-13.

【7】Xu X H, Wang X F. Near-infrared spectra noninvasive measurement method of glucose based on the “M+N” theory[J]. Research and Exploration in Laboratory, 2018, 37(2): 5-9, 14.
徐馨荷, 王晓飞. 基于“M+N”理论的近红外光谱血糖无创测量方法[J]. 实验室研究与探索, 2018, 37(2): 5-9, 14.

【8】Li L, Wang X F, Lu K. Near-infrared spectra noninvasive measurement method of blood oxygen saturation based on the “M+N” theory[J]. Journal of Biomedical Engineering, 2016, 33(5): 885-889.
李丽, 王晓飞, 卢恺. 基于“M+N”理论的近红外光谱血氧饱?#25237;?#26080;创测量方法[J]. 生物医学工程学杂志, 2016, 33(5): 885-889.

【9】Zhou Z H. Machine learning[M]. Beijing: Tsinghua University Press, 2016: 121-145.
周志华. 机器学习[M]. ?#26412;? 清华大学出版社, 2016: 121-145.

【10】Li G, Wang H Q, Zhao Z, et al. The quality evaluation of dynamic spectrum data[J]. Spectroscopy and Spectral Analysis, 2010, 30(10): 2802-2806.
李刚, 王慧泉, 赵喆, 等. 动态光?#36164;?#25454;质量的评价[J]. 光谱学与光谱分析, 2010, 30(10): 2802-2806.

【11】Li G, Xiong C, Wang H Q, et al. Single-trial estimation of dynamic spectrum[J]. Spectroscopy and Spectral Analysis, 2011, 31(7): 1857-1861.
李刚, 熊婵, 王慧泉, 等. 动态光谱的单拍提取[J]. 光谱学与光谱分析, 2011, 31(7): 1857-1861.

【12】Lin L, Li Y C, Wang M J, et al. D-value estimation of dynamic spectrum based on the statistical methods[J]. Spectroscopy and Spectral Analysis, 2012, 32(11): 3098-3102.
林凌, 李永城, 王蒙军, 等. 基于统?#21697;?#27861;的动态光谱差值提取[J]. 光谱学与光谱分析, 2012, 32(11): 3098-3102.

引用该论文

Wang Xiaofei,Zhang Xinyi,Xu Xinhe. Comparison of Multi-Factor-Considered Blood Glucose Prediction Models by Near-Infrared Spectroscopy[J]. Laser & Optoelectronics Progress, 2019, 56(4): 041701

王晓飞,张欣怡,徐馨荷. 考虑多种因素的近红外光谱血糖预测模型对比[J]. 激光与光电子学进展, 2019, 56(4): 041701

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF

手机十三水作弊软件