SPXY Sample Classification Method and Successive Projections Algorithm Combined with Near-Infrared Spectroscopy for the Determination of Total Sugar Content of Southern Xinjiang Jujube

Abstract

Sugar degree is an important indicator of red jujube internal quality. The main objectives of this paper are to minimize the collinearity between spectral variables, to find the variable groups which containing the lowest redundant information,and establish the model with better robustness by means of fewer variables. This paper uses SPXY (sample set partitioning based on joint x-y distances) to divide calibrating samples,and applies successive projections algorithm (SPA) to select the near-infrared spectral characteristic variable of southern Xinjiang jujube total sugar. To further establish the partial least squares (PLS) model with selected variables. The root mean square error of prediction (RMSEP) of the model is 2.8804. The correlation coefficient of prediction r is 0.9005.To compare the established PLS model results between SPA selecting variables and full spectrum. The results showed that: Firstly, the divided calibrating samples is reasonable in SPXY way.Secondly, SPA optimizes 9 variables of the full spectrum 1557 variables,and prediction effect of the established PLS model is better than the full spectrum PLS model.Finally,SPA can effectively select characteristic wavelength of component under test.