Department of Animal Production, ETSIAM, Universidad de Córdoba, 14071 Cordoba, Spain.
Talanta. 2009 Nov 15;80(1):48-53. doi: 10.1016/j.talanta.2009.06.026. Epub 2009 Jun 17.
This study develops a methodology based on NIR-microscopy analysis and chemometric tools for the detection of animal protein by-products in mixtures, such as compound feeds and mixtures of ingredients, using a library of animal meal by-products only. The proposed methodology is a two-step strategy which worked better than the SIMCA approach it was compared with. In the first step, animal particles are identified using one of two methods, a global or a local distance measure. In the second, K-nearest-neighbours (KNN) is used to discriminate between terrestrial and fish particles. The models were developed using a training set comprising 11,727 spectra of pure terrestrial meals and 5843 of fish meals. KNN using second derivative spectra and five neighbours correctly classifies 98.5% of these samples under cross-validation. The procedure was validated using two external datasets, one made up of mixtures of species (fish and bovine), and a second of commercial compound feeds. The results obtained confirm that the procedure is able to reliably detect the presence of animal meals, although further work would be needed to develop it into an accurate quantitative method.
本研究开发了一种基于 NIR 显微镜分析和化学计量学工具的方法，用于检测混合物（如配合饲料和成分混合物）中的动物蛋白副产品，仅使用动物饲料副产品库。所提出的方法是一种两步策略，比与之比较的 SIMCA 方法效果更好。在第一步中，使用全局或局部距离度量标准中的一种方法来识别动物颗粒。在第二步中，使用 K 最近邻 (KNN) 来区分陆地和鱼类颗粒。模型使用包含 11727 个纯陆地餐和 5843 个鱼餐的纯光谱集进行开发。使用二阶导数光谱和五个近邻的 KNN 在交叉验证下正确分类 98.5%的这些样本。该程序使用两个外部数据集进行验证，一个由物种（鱼类和牛）混合物组成，另一个由商业配合饲料组成。所得结果证实，该程序能够可靠地检测动物饲料的存在，尽管需要进一步的工作才能将其开发成一种准确的定量方法。
