Classification of rapeseed colors using Fourier transform mid-infrared photoacoustic spectroscopy
Abstract
Fourier transform mid-infrared photoacoustic spectroscopy (FTIR-PAS) combined with multivariate discriminant analysis was employed to classify colors of rapeseeds. A total of 129 rapeseed varieties representing three colors (black, reddish and mottled-yellow) were scanned in the range of 500–4000 cm−1. A Savitzky–Golay algorithm was used for the spectral pretreatment. Principal components analysis (PCA) gave an overview of sample distribution in the score space of principal components. The whole sample set was divided into calibration and prediction sets, according to the Kennard–Stone algorithm. Classification models were developed using linear discriminant analysis combined with principal components analysis (PCA-LDA), partial least square discriminant analysis (PLS-DA), and support vector machine (SVM). Results showed that the best accuracy was achieved by the SVM model, with the overall error rates (ERs) of 1.1% and 2.5%, in calibration and prediction sets, respectively. Besides, the PLS-DA model performed slightly better than the PCA-LDA model. This work had demonstrated the good potential of FTIR-PAS to classify rapeseed colors.