Keywords : Partial Least Square Regression
European Journal of Molecular & Clinical Medicine,
2020, Volume 7, Issue 7, Pages 3506-3511
Aim of the study was to predict protein content of wheat grain stored for one year at 4˚C temperature using selected Near Infrared Near Infrared (NIR) wavelengths and Chemometrics. The spectra of grains were measured in reflectance mode with the use of lab built NIR filter based pre dispersive spectrometer ranging from wavelength 750nm to 2580 nm. Wavelength set was divided into two sets for all the stored samples. The chemometric methods applied to the reference data and recorded NIR data were analyzed based on principal component analysis (PCA) scores, partial last squared regression (PLSR) model. R2 values were 0.955, 0.997 for prediction of protein content from PLSR Wavelength Set I and II respectively. Wavelengths with high β correlation coefficients were defined. This study showed that near infrared spectroscopy has potential to distinguish wheat grains stored refrigerator conditions.