Recognition of organic rice samples based on trace elements and support vector machines

Barbosa, Rommel M.; de Paula, Eloisa Silva; Paulelli, Ana Carolina; Moore, Anthony F.; Souza, Juliana Maria Oliveira; Batista, Bruno Lemos; Campiglia, Andres D.; Barbosa, Fernando

Recognition of organic rice samples based on trace elements and support vector machines

2016

A simple approach is proposed for the authentication of organic rice samples. The strategy combines levels of concentration of trace elements and a data mining technique known as support vector machine (SVM). Nineteen elements (As, B, Ba, Ca, Cd, Ce, Cr, Co, Cu, Fe, La, Mg, Mn, Mo, P, Pb, Rb, Se and Zn) were determined in organic (n=17) and conventional (n=33) rice samples by quadrupole inductively coupled plasma mass spectrometry (q-ICP-MS) and the variations found in their elemental composition resulted in profiles with useful information for classification purposes. With the proposed methodology, it was possible to predict the authenticity of organic rice samples with an accuracy of 98% when using the 19 original elements. An accuracy of 96% was found using only the elements Ca and Cd.

显示更多 [+]