Share Email Print

Proceedings Paper • new

Quantitative evaluation of glucose spectra from NIR spectroscopy measurements using PLS regression analysis
Format Member Price Non-Member Price
PDF $14.40 $18.00
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

The quantitative evaluations were carried out in NIR spectroscopy that was implemented for monitoring and predicting the concentration of glucose samples. The collected absorbance data was preprocessed in developing PLS model before calibration using Savitzky-Golay filter. The spectrum was corrected by subtracting the offset of the regression to the absorption value and dividing this difference by the slope using Leave One Out Cross Validation (LOOCV) of the training set to determine the optimum number of PLS components. The Samples of glucose solution consist of 21 different molarity from 3000 to 5000 mg/dl with the interval of 100 mg/dl in step. Results obtained shown the linear dependency of the reference and predicted glucose concentration, with RMSECV and R2CV value are 104.92 mg/dl and 0.9728, respectively. The RMSECV shown the lowest error present and R2CV were close to one, indicates that the PLS model suited to accurately predict the variability glucose concentration.

Paper Details

Date Published: 11 April 2019
PDF: 3 pages
Proc. SPIE 11044, Third International Seminar on Photonics, Optics, and Its Applications (ISPhOA 2018), 110440J (11 April 2019); doi: 10.1117/12.2504852
Show Author Affiliations
S. Hepriyadi, Institut Teknologi Sepuluh Nopember (Indonesia)
I. Setiadi, Institut Teknologi Sepuluh Nopember (Indonesia)
A. Nasution, Institut Teknologi Sepuluh Nopember (Indonesia)

Published in SPIE Proceedings Vol. 11044:
Third International Seminar on Photonics, Optics, and Its Applications (ISPhOA 2018)
Aulia M. T. Nasution; Agus Muhamad Hatta, Editor(s)

© SPIE. Terms of Use
Back to Top