Classification of the Varieties of Walnut Powder by Laser-induced Breakdown Spectroscopy and Chemometrics

Abstract

Abstract. The rapid classification of the varieties of walnut powder is important to protect the consumers against potential fraud, since different varieties of walnut powder vary dramatically in quality, taste and sale price. Laser-induced breakdown spectroscopy (LIBS) is a promising technology for on-line application, which is no or little sample preparation, fast analysis speed (usually seconds to minutes), remote detection available. In this study, laser-induced breakdown spectroscopy and multi-variable analysis methods were applied to classify varieties of walnut powder for the first time. Before LIBS analysis, a fairly flat surface was provided to reduce fluctuation, and no other sample preparation was needed. After acquiring the LIBS spectra, Principal Component Analysis (PCA) was used to make qualitative discrimination, and classification models were developed with Partial Least Squares Discrimination Analysis (PLS-DA) and Support Vector Machines (SVM). Three origins and different varieties from same origin were discriminated by LIBS. It was shown that origins as well as different varieties from the same origin could be differentiated successfully by laser-induced breakdown spectroscopy and chemometrics. Support vector machines can help to handle complex LIBS dataset, which improved the classified rate of model. The presented results provide the first proof-of-principle data for the on-line application of LIBS technology for classification of the varieties of walnut powder.