J4

• 计算机科学 • 上一篇    下一篇

人工神经网络-红外光谱法对人体血糖的无创监测分析

左 平1,2, 李映红3, 韩 笑1, 马驷良1   

  1. 1. 吉林大学 数学学院, 长春 130012; 2. 空军航空大学 基础部, 长春 130022;3. 长春大学 理学院, 长春 130022
  • 收稿日期:2008-03-03 修回日期:1900-01-01 出版日期:2008-11-26 发布日期:2008-11-26
  • 通讯作者: 马驷良

Analysis of Noninvasive Measurement of Human Blood Glucosewith ANNNIR Spectroscopy

ZUO Ping1,2, LI Ying hong3, HAN Xiao1, MA Siliang1   

  1. 1. College of Mathematics, Jilin University, Changchun 130012, China;2. Department of Foundation, Aviation University of Air Force, Changchun 130022, China;3. College of Sciences, Changchun University, Changchun 130022, China
  • Received:2008-03-03 Revised:1900-01-01 Online:2008-11-26 Published:2008-11-26
  • Contact: MA Siliang

摘要: 针对人体血糖无创监测的近红外光谱分析, 提出一种血液红外吸收光谱分析的新技术, 通过对正常人的全血和血清与高糖全血的红外吸收光谱进行测量, 应用人工神经网络BP算法, 以16个特征波长处的吸收值作为网络特征参数, 进行网络训练. 结果表明, 网络训练11次即可达到误差精度要求, 误差在-0.01~0.03 mmol/L, 达到了国家计量检测规程关于生化分析的要求.

关键词: 红外吸收光谱, 人工神经网络, 无创血糖检测

Abstract: Based on the near infrared absorption spectrum analysis of noninvasive blood glucose, this paper puts forward a new technique for t he infrared absorption spectrum analysis of blood. By means of the measurement of in frared absorption spectra of the normal people’s whole blood, serum and high  glucose’s whole blood, application of the artificial neural network BP arithmetic, and with the absorption values of sixteen characteristic wavelengths as the network characteristic parameters, the network training was carried out. Only repeating 11 times, can the network training reach the error precision required. The error between -0.01~0.03 mmol/L fulfils the requirement of national metrological verification regulation on biochemical analysis. This research result shows valuable prospects for blood infrared absorption spectrum analysis and disease diagnoses.

Key words: infrared absorption spectrum, artificial neural network, noninvasive blood glucose measurement

中图分类号: 

  • TP391