Optimization of Informative Spectral Regions in FT-NIR Spectroscopy for Measuring the Soluble Solids Content of Apple

Abstract

A novel potential method, linear combination weight PLS (LCW-PLS) model, was suggested for improving the performance of routine PLS model based on selected informative regions. Moving window partial least squares (MWPLS), genetic algorithms interval partial least squares (GAiPLS) and synergy interval partial least squares (SiPLS) were used to optimize informative spectral regions from FT-NIR spectra. A total of 660 apples harvested at 2006, 2007 and 2008, were divided into calibration and prediction sets by Kennard-Stone method. The best calibration model was obtained by LCW-PLS method based on informative spectral regions of 4328-4787, 5323-5512, 5982-7135 and 7159-7463 cm 21 selected by MWPLS procedure, and corresponding weights of 0.004, 0.070, 0.066 and 0.860, respectively. The LCW-MWPLS model was applied to predict samples, the prediction results were with R P of 0.942, RMSEP of 0.649 %Brix and RPD P of 3.10. In addition, developed LCW-MWPLS model using random two years samples was used to predict one year samples excluded. The predictive results were with R P of 0.921-0.927, RMSEP of 0.714-0.795 %Brix and RPD P of 2.44-2.88. The LCW-MWPLS model giving a prediction error equal to 4% of fresh weight was sufficiently accurate to determine the SSC of apple non-destructively.

Determining sugar content and firmness of ‘Fuji’ apples by using portable near‐infrared spectrometer and diffuse transmittance spectroscopy

“…Contrasted with the published data on sugar content determination for apples using NIR spectroscopy, the lowest RMSEP (0.570 °Brix) obtained here is a little higher than that reported in some studies (Fan et al, ; Giovanelli et al, ; Lu et al, ; Pissard et al, ; Qi et al, ; Zou et al, ), but lower than that reported 0.649 °Brix by Wang, Cheng, Liu, Tang, and Han (). It is much lower than that reported by using hyperspectral imaging technique (Dong, Guo, Wang, Liu, & Zhao, ; Huang & Lu, ; Mendoza, Lu, Ariana, Cen, & Bailey, ; Noh & Lu, ; Peng & Lu, ), and by applying dielectric spectra (Guo, Shang, Zhu, & Nelson, b).…”