Quantitative evaluation of glucose spectra from NIR spectroscopy measurements using PLS regression analysis

S. Hepriyadi; I. Setiadi; A. Nasution

doi:10.1117/12.2504852

11 April 2019 Quantitative evaluation of glucose spectra from NIR spectroscopy measurements using PLS regression analysis

S. Hepriyadi, I. Setiadi, A. Nasution

Author Affiliations +

Proceedings Volume 11044, Third International Seminar on Photonics, Optics, and Its Applications (ISPhOA 2018); 110440J (2019) https://doi.org/10.1117/12.2504852
Event: Third International Seminar on Photonics, Optics, and Its Applications (ISPhOA 2018), 2018, Surabaya, Indonesia

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.

Citation Download Citation

S. Hepriyadi, I. Setiadi, and A. Nasution "Quantitative evaluation of glucose spectra from NIR spectroscopy measurements using PLS regression analysis", Proc. SPIE 11044, Third International Seminar on Photonics, Optics, and Its Applications (ISPhOA 2018), 110440J (11 April 2019); https://doi.org/10.1117/12.2504852

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available