Institute of Basic and Applied Chemistry of the Northeast of Argentina (IQUIBA-NEA), National Scientific and Technical Research Council (CONICET), Faculty of Exact and Natural Science and Surveying, National University of the Northeast - UNNE, Av. Libertad 5470, 3400 Corrientes, Argentina.
Faculty of Agricultural Sciences, UNNE, Sgto. Cabral 2131, 3400 Corrientes, Argentina.
Food Chem. 2019 Nov 1;297:124960. doi: 10.1016/j.foodchem.2019.124960. Epub 2019 Jun 8.
Rice is the most consumed food worldwide, therefore its designation of origin (PDO) is very useful. Laser-induced breakdown spectroscopy (LIBS) is an interesting analytical technique for PDO certification, since it provides fast multielemental analysis requiring minimal sample treatment. In this work LIBS spectral data from rice analysis were evaluated for PDO certification of Argentine brown rice. Samples from two PDOs were analyzed by LIBS coupled to spark discharge. The selection of spectral data was accomplished by extreme gradient boosting (XGBoost), an algorithm currently used in machine learning, but rarely applied in chemical issues. Emission lines of C, Ca, Fe, Mg and Na were selected, and the best performance of classification were obtained using k-nearest neighbor (k-NN) algorithm. The developed method provided 84% of accuracy, 100% of sensitivity and 78% of specificity in classification of test samples. Furthermore, it is simple, clean and can be easily applied for rice certification.
大米是世界上消费最多的食物，因此其原产地名称（PDO）非常有用。激光诱导击穿光谱（LIBS）是一种用于 PDO 认证的有趣分析技术，因为它提供了快速的多元素分析，只需最小的样品处理。在这项工作中，评估了来自大米分析的 LIBS 光谱数据，以对阿根廷糙米进行 PDO 认证。LIBS 与火花放电耦合分析了来自两个 PDO 的样品。光谱数据的选择是通过极端梯度提升（XGBoost）完成的，这是一种目前在机器学习中使用但很少应用于化学问题的算法。选择了 C、Ca、Fe、Mg 和 Na 的发射线，并使用 k-最近邻（k-NN）算法获得了最佳的分类性能。所开发的方法在测试样品的分类中提供了 84%的准确率、100%的灵敏度和 78%的特异性。此外，它简单、清洁，易于应用于大米认证。
