WINDOW SUBTRACTED WAVE BAND SELECTION METHOD FOR THE FTIR/ATR SPECTRUM ANALYSIS
Author(s) -
Jun Xie,
Han Zhang,
Jianfeng Li,
Fuhong Cai
Publication year - 2018
Publication title -
progress in electromagnetics research m
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.216
H-Index - 31
ISSN - 1937-8726
DOI - 10.2528/pierm17110705
Subject(s) - window (computing) , selection (genetic algorithm) , spectrum (functional analysis) , fourier transform infrared spectroscopy , physics , optics , computer science , artificial intelligence , quantum mechanics , operating system
The rapid quantification method of human serum glucose was established by using the Fourier transform infrared spectroscopy (FTIR) and attenuated total reflection (ATR). Based on the optimal predicting effect, a subtraction band model combining with optimal single continuous wave band was developed. The spectrum (1600–900 cm−1) was selected as the base band. Then, window subtracted partial least squares (WSPLS) based on the spectrum was carried out, and the optimal two continuous bands were found. The results show that the prediction effect of the base band model is obviously better than that of the whole spectral model, and WSPLS model is even better than base band model. Finally, an independent test set was tested for model verification. V-SEP and V-RP were 0.831 mmol/L and 0.882, respectively by the compensation model.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom