Portable Near-Infrared Spectrometer in Tandem with Chemometrics as an Option for the Authenticating Commercial A2 Bovine Milk

Abstract

The identification of genetic forms of proteins in milk can be achieved through genetic analysis and presents challenges and high time consumption for assessing the authenticity of A2 milk. In this context, the study focused on evaluating the possibility of authenticating A2 milk against non-A2 milk and their mixtures using a portable NIR spectrometer, the MicroNIR, combined with a one-class method. 63 samples of whole A2 milk were selected (authentic set), and 40 samples (fraudulent set) composed of non-A2 milk and mixtures in 3 different proportions (10, 25, and 50% v/v) of non-A2 milk in A2 milk. For spectra collection, a MicroNIR was used. Full data were pre-processed using different methods, but the most effective approach was the combination of the first derivative with Savitzky-Golay smoothing and Standard Normal Variate (SNV). A Data-driven Soft Independent Modeling of Class Analogy (DD-SIMCA) was applied. Using the Kennard-Stone algorithm, the authentic samples were split into two sets (45 for calibration and 20 for external validation). The non-A2 and fraudulent samples were added to the external validation set, and the model’s performance was evaluated using the metrics of sensitivity, specificity, accuracy, and precision. The DD-SIMCA model, utilizing 2 PCs, showed excellent performance, with 100% results in all metrics, indicating no errors in the recognition of authentic samples. This performance makes the model suitable for use with portable equipment. Additionally, this fast and non-invasive technique can be optimized for applications in industrial management, food control, and A2 product authentication.