ABSTRACT
Partial least squares regression (PLSR) is a statistical method, a multivariate calibration technique that bears some relationship with principal components regression. The mean spectra of the samples were extracted from the hyperspectral images, and multivariate calibration models were built using PLSR for predicting water, fat, and protein contents. The feature wavelengths were identified using regression coefficients resulting from the PLSR analyses. The weighted regression coefficients of the resulting PLSR models were used to identify the most important wavelengths and to reduce the high dimensionality of the hyperspectral data. PLSR, principal component analysis, support vector machine, and artificial neural network models were created to predict the sweetness and hardness values in melons from the hyperspectral data. M. Kamruzzaman et al investigated the potential of hyperspectral imaging in the near-infrared range of 900–1,700 nm for non-destructive prediction of chemical composition of lamb meat.
