Determination of semolina adulteration by NIR spectroscopy; Determinación de la adulteración de sémola mediante espectroscopia NIR

Abstract

The objective was to implement a semolina percentage recognition system using near-infrared spectroscopy (NIR) and multivariate data analysis. For this purpose, 6 samples were an aly zed with different percentages ofsemolina(20, 4 0, 6 0, 8 0 an d 100 %). Samples were repeated 20 times. The observed NIR sp ect rum was absorbance in the range of 1100 and 2500 nm. In order to reduce the data, the analysis of main components was used by testing 24 classification models, from which the one that reached the highest level of precision was the Linear Support Vector Machine (SVM) algorithm, reaching 98.8%, achieving fairly satisfactory discriminatio n with values of PC1 (99.7%), PC2 (0.3%) and PC3 (0.1%), reachin g a total cumulative variation of the contribution of th e first 3 P Cs o f 99.9%. Partial Least Regression (PLS) models applied to NIR- spectra showed R2 between 0.9388. These values demonstrated that NIR spectroscopy can be used for the identification and quantification o f fiber added to semolina