“…In this study, the size of one ROI image was about 8,500 pixels, and each pixel spectrum included 1,288 wavelengths. Considering the redundancy and collinearity of hyperspectral data, it is essential to reduce the dimension of spectral data (Lee, Kim, Lee, & Cho, ; Siripatrawan & Makino, ). Several wavelengths (variables) selection methods, namely, uninformative variable elimination (UVE), competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), regression coefficients (RC), and the combination of different variable algorithms, were used to choose characteristic wavelengths from full spectrum ranges for optimizing the modeling procedures.…”