Abstract
Two different near infrared spectrometric systems were used to determine soluble solids content (SSC) of intact apple, including a portable near infrared (NIR) spectrometer and an online NIR system. The pretreatment methods were applied to improve the predictive results. The moving average smoothing was significant. The effective wavelength regions were chosen by interval partial least squares (iPLS) and backward iPLS (Bipls). Then the models were developed by partial least square regression (PLSR) and least square support machine (LS-SVM). Performance comparisons were made in the context of 30 unknown samples prediction. The LS-SVM models were better than others with correlation coefficient (R) and root mean square error of prediction (RMSEP) of (0.88, 0.80oBrix) and (0.82, 1.01oBrix) for portable and online measurement mode, respectively. The results demonstrated that the online measurement mode was not as well as the portable.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call