Abstract

In order to investigate a fast and efficient method determining the freshness of bee pollen, visible and near-infrared (Vis-NIR) reflectance spectroscopy with least squares-support vector machines (LS-SVM) was applied to determine storage period of bee pollen. The Camellia bee pollens stored for 4~50(47) days at room temperature were investigated. Spectra were collected by an ASD Fieldspec spectrometer as the input variables to build the LS-SVM model. Results show that the prediction performance of LS-SVM model is better than partial least square (PLS) and principal component regression (PCR). Its correlation coefficient of prediction set (rp) is 0.996, standard error of prediction (SEP) is 1.310, and root mean square error of prediction (RMSEP) is 1.308. It is concluded that Vis-NIR spectroscopy with LS-SVM is a feasible method to determine the storage period of bee pollen. Moreover, the results for different storage periods were compared. It is shown that the storage periods between 11~50 can be well determined by LS-SVM.

Full Text
Published version (Free)

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