Fast Discrimination of Juicy Peach Varieties by Vis/NIR Spectroscopy Based on Bayesian-SDA and PCA
Visible/Near-infrared reflectance spectroscopy (Vis/NIRS) was applied to variety discrimination of juicy peach. A total of 75 samples were investigated for Vis/NIRS using a field spectroradiometer. Chemometrics was used to build the relationship between the absorbance spectra and varieties. Principle component analysis (PCA) was executed to reduce numerous wavebands into 8 principle components (PCs) as variables of stepwise discrimination analysis (SDA). After execution of SDA through variables selection with 21 samples as validation set, the final results shown an excellent performance of 100% varieties discrimination which was better than the one only predicted by using partial least squares (PLS) model. The results showed the potential ability of Vis/NIRS coupled with SDA-PCA algorithm to discriminate the varieties of juicy peach. The analysis model was rapid, objective and accurate.
KeywordsPartial Little Square Principle Component Analysis Partial Little Square Regression Partial Little Square Model Partial Little Square
Unable to display preview. Download preview PDF.
- 4.Slaughter, D.C.: Non-destructive Determination of Internal Quality in Peaches and Nectarines. Transactions of the ASAE 38(2), 617–623 (1995)Google Scholar
- 6.Wold, H., Krishnaiah, P.R. (eds.): 391–420. Academic Press, New York (1966)Google Scholar
- 8.Martens, H., Naes, T.: Mulutivariate Calibration. Wiley, New York (1998)Google Scholar
- 9.Fisher, R.A.: The Use of Multiple Measurements in Taxonomic Problems. Annals of Eugenics 7(2), 179–188 (1936)Google Scholar