Classification of edible oils and modeling of their physico-chemical properties by chemometric methods using mid-IR spectroscopy.

摘要: This research work describes two studies for the classification and characterization of edible oils its quality parameters through Fourier transform mid infrared spectroscopy (FT-mid-IR) together with chemometric methods. The discrimination canola, sunflower, corn soybean was investigated using SVM-DA, SIMCA PLS-DA. Using FT-mid-IR, DPLS able to classify 100% samples from validation set, but SVM-DA were not. parameters: refraction index relative density obtained reference Prediction models FT-mid-IR spectra calculated these partial least squares (PLS) support vector machines (SVM). Several preprocessing alternatives (first derivative, multiplicative scatter correction, mean centering, standard normal variate) investigated. best result achieved SVM as well except when combination centering first derivative used. For both parameters, results figures merit expressed by root square error cross (RMSECV) prediction (RMSEP) equal 0.0001.