Abstract
It is very crucial that arepresentative training set can be extracted from a pool of real samples. Inthis paper, a representative set of correction samples of wheat protein contentis selected by using SPXY algorithm firstly; Secondly, the spectral data ispretreated to enhance spectral features; Thirdly, the model of wheat grainprotein is established by using partial least squares regression. The resultsshow that the model established by the calibration set selected by SPXY isbetter than the model established by the calibration set selected randomly.Root mean square error of prediction(RMSEP) and prediction correlationcoefficient(R) are 0.41094 and 0.97705 respectively, which are similar to themodel established by the initial calibration set.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have