Determination of glucose concentration from near infrared spectra using least square support vector machine

Author

Malik, Bilal Ahmad

Author_Institution

Sci. & Instrum. Centre, Univ. of Kashmir, Srinagar, India

fYear

2015

fDate

28-30 May 2015

Firstpage

475

Lastpage

478

Abstract

One of the many challenges for translating noninvasive glucose measurement into clinical practice is the calibration of the measuring instrument. In this work, least squares support vector regression (LS-SVR) has been used to develop a multivariate calibration model for determination of glucose concentration from near infra-red (NIR) spectra. The behaviour of developed model is studied on NIR spectra of a mixture composed of glucose, urea, and triacetin which spans from 2100 nm to 2400 nm with a spectral resolution of 1nm. The proposed model improved the standard error of prediction (SEP) from 49.4 mg/dL in case of Principal Component Regression (PCR) and 27.5 mg/dL in case of Principal Least Squares Regression (PLSR) to 19.4mg/dL.

Keywords

biochemistry; calibration; chemical variables measurement; infrared spectra; least squares approximations; medical computing; principal component analysis; regression analysis; sugar; support vector machines; LS-SVR; NIR spectra; PCR; PLSR; SEP; clinical practice; glucose concentration; least square support vector machine; least squares support vector regression; mixture; multivariate calibration; near infrared spectra; noninvasive glucose measurement; principal component regression; principal least squares regression; spectral resolution; standard error-of-prediction; Calibration; Diabetes; Kernel; Predictive models; Spectroscopy; Sugar; Support vector machines; Calibration; LS-SVM; Machine Learning; NIR; Non-invasive glucose measurement; SEC; SEP;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Instrumentation and Control (ICIC), 2015 International Conference on

Conference_Location

Pune

Type

conf

DOI

10.1109/IIC.2015.7150789

Filename

7150789