This is the authors' abstract. We don't add key points for this paper.
A portable near-infrared (NIR) instrument was developed for predicting soluble solids content (SSC) of pears equipped with light emitting diodes (LEDs). NIR spectra were collected on the calibration and prediction sets (145:45). Relationships between spectra and SSC were developed by multivariate linear regression (MLR), partial least squares (PLS) and artificial neural networks (ANNs) in the calibration set. The 45 unknown pears were applied to evaluate the performance of them in terms of root mean square errors of prediction (RMSEP) and correlation coefficients (r). The best result was obtained by PLS with RMSEP of 0.62°Brix and r of 0.82. The results showed that the SSC of pears could be predicted by the portable NIR instrument.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2011) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: