Genetic Multivariate Calibration Methods for Near Infrared (NIR) Spectroscopic Determination of Complex Mixtures

Authors : Durmuş ÖZDEMİR and Betül ÖZTÜRK

Pages : 497-514

View : 24 | Download : 12

Publication Date : 0000-00-00

Article Type : Research Paper

Abstract :The simultaneous determination of ternary mixtures of methylene chloride, ethyl acetate, and methanol using near infrared insert ignore into journalissuearticles values(NIR); spectroscopy and 4 different genetic algorithms based multivariate calibration methods was demonstrated. The 4 genetic multivariate calibration methods are genetic partial least squares insert ignore into journalissuearticles values(GPLS);, genetic regression insert ignore into journalissuearticles values(GR);, genetic classical least squares insert ignore into journalissuearticles values(GCLS); and genetic inverse least squares insert ignore into journalissuearticles values(GILS);. The sample data set contains the NIR spectra of 63 ternary mixtures and covers the range from 900 to 2000 nm in 2 nm intervals. Of these 63 spectra, 42 were used as the calibration set, and 21 were reserved for the prediction purposes. Several calibration models were built with the 4 genetic algorithm based methods for each component that makes up the mixtures. Overall, the standard error of calibration insert ignore into journalissuearticles values(SEC); and the standard error of prediction insert ignore into journalissuearticles values(SEP); were in the range of 0.22 to 2.5 insert ignore into journalissuearticles values(% by volume insert ignore into journalissuearticles values(v/v);); for all the 4 methods. A comparison of genetic algorithm selected wavelengths for each component and for each method was also included.
Keywords : Near infrared spectroscopy, Multivariate calibration, Genetic algorithms, Genetic Regression, Partial Least Squares, Classical Least Squares, Inverse Least Squares