Journal
MONATSHEFTE FUR CHEMIE
Volume 149, Issue 8, Pages 1341-1347Publisher
SPRINGER WIEN
DOI: 10.1007/s00706-018-2213-z
Keywords
ATR-FTIR spectrometry; Partial least squares; Least squares support vector machine; BTX determination
Categories
Ask authors/readers for more resources
An analytical method for rapid and simultaneous quantitative determination of benzene, toluene, and xylenes in complex hydrocarbon mixtures has been proposed. The method consists of obtaining infrared absorption data by attenuated total reflectance Fourier transform infrared spectrometric method in the fingerprint region (630-1000 cm(-1)). The spectroscopic data were treated by partial least squares and least squares support vector machine (LS-SVM) methods. The LS-SVM results were obtained using radial basis function and parameter optimization was performed using the simplex method. Root mean squares of cross-validation (RMSECV) values of 0.34 for benzene, 1.85 for toluene, and 1.24 for xylenes using PLS algorithm and RMSECV values of 0.37 for benzene, 1.34 for toluene, and 1.1 for xylenes using LS-SVM algorithm were obtained. [GRAPHICS] .
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available