Quantitative analysis of glucose in whole blood using FT-Raman spectroscopy and artificial neural network

DOI

10.2991/iccse-15.2015.87How to use a DOI?

Keywords

FT-Raman spectroscopy, Glucose, Artificial neural network, Whole blood

Abstract

In this paper, the FT-Raman spectroscopy and artificial neural network were used to quantify the glucose concentration in the whole blood. The quantitative analysis was performed through the artificial neural network (ANN) associated to training set selection strategy method. All analysis was carried out by whole spectrum. The ANN model with the highest r2, the lowest values of root mean square error (RMSE) for both training and validation data was used in our work. The results indicated that the FT-Raman spectroscopy and ANN is a rapid, simple, and efficient method to quantitative analysis of glucose in the whole blood.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Qiaoyun Wang
AU  - Nianzu Zheng
AU  - Zhigang Li
AU  - Zhenhe Ma
PY  - 2015/07
DA  - 2015/07
TI  - Quantitative analysis of glucose in whole blood using FT-Raman spectroscopy and artificial neural network
BT  - Proceedings of the 2015 International Conference on Computational Science and Engineering
PB  - Atlantis Press
SP  - 471
EP  - 475
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccse-15.2015.87
DO  - 10.2991/iccse-15.2015.87
ID  - Wang2015/07
ER  -