Share Email Print
cover

Proceedings Paper

Comparison of three chemometrics methods for near-infrared spectra of glucose in the whole blood
Author(s): Hongyan Zhang; Dong Ding; Xin Li; Yu Chen; Yuguo Tang
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Principal Component Regression (PCR), Partial Least Square (PLS) and Artificial Neural Networks (ANN) methods are used in the analysis for the near infrared (NIR) spectra of glucose in the whole blood. The calibration model is built up in the spectrum band where there are the glucose has much more spectral absorption than the water, fat, and protein with these methods and the correlation coefficients of the model are showed in this paper. Comparing these results, a suitable method to analyze the glucose NIR spectrum in the whole blood is found.

Paper Details

Date Published: 10 January 2005
PDF: 8 pages
Proc. SPIE 5640, Infrared Components and Their Applications, (10 January 2005); doi: 10.1117/12.572350
Show Author Affiliations
Hongyan Zhang, Changchun Institute of Optics, Fine Mechanics and Physics, CAS (China)
Dong Ding, Jilin Univ. (China)
Xin Li, Changchun Institute of Optics, Fine Mechanics and Physics, CAS (China)
Yu Chen, Changchun Institute of Optics, Fine Mechanics and Physics, CAS (China)
Yuguo Tang, Changchun Institute of Optics, Fine Mechanics and Physics, CAS (China)


Published in SPIE Proceedings Vol. 5640:
Infrared Components and Their Applications
Haimei Gong; Yi Cai; Jean-Pierre Chatard, Editor(s)

© SPIE. Terms of Use
Back to Top