Millatina Nela Rifda Nur, Calle José Luis Pérez, Barea-Sepúlveda Marta, Setyaningsih Widiastuti, Palma Miguel
Department of Food and Agricultural Product Technology, Faculty of Agricultural Technology, Universitas Gadjah Mada, Jalan Flora, Bulaksumur, 55281 Yogyakarta, Indonesia.
Department of Analytical Chemistry, Faculty of Sciences, IVAGRO, University of Cadiz, Campus de Excelencia Internacional Agroalimentario (CeiA3), Campus del Rio San Pedro, 11510, Puerto Real, Cádiz, Spain.
Food Chem. 2024 Aug 15;449:139212. doi: 10.1016/j.foodchem.2024.139212. Epub 2024 Apr 2.
The rising demand for cocoa powder has resulted in an upsurge in market prices, leading to the emergence of adulteration practices aimed at achieving economic benefits. This study aimed to detect and quantify cocoa powder adulteration using visible and near-infrared spectroscopy (Vis-NIRS). The adulterants used in this study were powdered carob, cocoa shell, foxtail millet, soybean, and whole wheat. The NIRS data could not be resolved using Savitzky-Golay smoothing. Nevertheless, the application of a random forest and support vector machine successfully classified the samples with 100% accuracy. Quantification of adulteration using partial least squares (PLS), Lasso, Ridge, elastic Net, and RF regressions provided R higher than 0.96 and root mean square error <2.6. Coupling PLS with the Boruta algorithm produced the most reliable regression model (R = 1, RMSE = 0.0000). Finally, an online application was prepared to facilitate the determination of adulterants in the cocoa powder.
对可可粉需求的不断增加导致市场价格飙升，从而催生了旨在获取经济利益的掺假行为。本研究旨在利用可见-近红外光谱法（Vis-NIRS）检测并量化可可粉掺假情况。本研究中使用的掺假物有角豆粉、可可壳、粟、大豆和全麦。Savitzky-Golay平滑法无法解析近红外光谱数据。然而，随机森林和支持向量机的应用成功地以100%的准确率对样品进行了分类。使用偏最小二乘法（PLS）、套索回归、岭回归、弹性网络回归和随机森林回归对掺假进行量化，所得R值高于0.96，均方根误差<2.6。将PLS与Boruta算法相结合产生了最可靠的回归模型（R = 1，RMSE = 0.0000）。最后，编写了一个在线应用程序，以方便测定可可粉中的掺假物。
