Classifying rapeseed varieties using Fourier transform infrared photoacoustic spectroscopy (FTIR-PAS)

• Published in: Computers and electronics in agriculture Vol. 107; pp. 58 - 63
• Main Authors: Lu, Yuzhen, Du, Changwen, Yu, Changbing, Zhou, Jianmin
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier 01.09.2014
• Subjects: Agronomy. Soil science and plant productions; Algorithms; Biological and medical sciences; Classification; Fourier transforms; Fundamental and applied biological sciences. Psychology; Infrared; Mathematical models; Photoacoustic spectroscopy; Rapeseed; Support vector machines; Discriminant analysis; Fourier transformation; Brassica napus var. oleifera; Rapeseeds; Support vector machine; Algorithm; Infrared spectrometry; Fourier transform infrared photoacoustic spectroscopy (FTIR-PAS); Cruciferae; Rapeseed; Optoacoustical spectrometry; Partial least squares-discriminant analysis (PLS-DA); Dicotyledones; Angiospermae; Classification; Successive projections algorithm (SPA); Spermatophyta; Fourier-transformed infrared spectrometry; Variety classification; Partial least squares; Oil plant (vegetal); Support vector machines (SVM)
• ISSN: 0168-1699; 1872-7107
• DOI: 10.1016/j.compag.2014.06.005

This study proposed a methodology for classification of rapeseed varieties using Fourier transform infrared photoacoustic spectroscopy (FTIR-PAS). For this purpose, principal components analysis (PCA) was first used to reveal the separation of three varieties of rapeseeds, and then partial least squares-discriminant analysis (PLS-DA) and support vector machines (SVM) were employed for the classification task. The overall classification error rates (ERs) of prediction set were 7.5% and 0 for the models of PLS-DA and SVM, respectively. Furthermore, successive projections algorithm (SPA) was adopted to choose an appropriate variable subset as the inputs of PLS-DA and SVM. Both SPA-PLS-DA and SPA-SVM models gave improved predictive accuracy with significantly reduced model variables. The results of this study had showed the good performance of FTIR-PAS as a rapid, non-destructive and objective tool for classifying varieties of rapeseeds.