UV Raman spectroscopy for the characterization of strongly fluorescing beverages

Integration of surface-enhanced Raman spectroscopy (SERS) and machine learning tools for coffee beverage classification

Surface-enhanced Raman spectroscopy (SERS) is a powerful tool for molecule identification. However, profiling complex samples remains a challenge because SERS peaks are likely to overlap, confounding features when multiple analytes are present in a single sample. In addition, SERS often suffers from high variability in signal enhancement due to nonuniform SERS substrate. The machine learning classification techniques widely used for facial recognition are excellent tools to overcome the complexity of SERS data interpretation. Herein, we reported a sensor for classifying coffee beverages by integrating SERS, feature extractions, and machine learning classifiers. A versatile and low-cost SERS substrate, called nanopaper, was used to enhance Raman signals of dilute compounds in coffee beverages. Two classic multivariate analysis techniques, Principal Component Analysis (PCA) and Discriminant Analysis of Principal Components (DAPC), were used to extract the significant spectral features, and the performance of various machine learning classifiers was evaluated. The combination of DAPC with Support Vector Machine (SVM) or K-Nearest Neighbor (KNN) shows the best performance for classifying coffee beverages. This user-friendly and versatile sensor has the potential to be a practical quality-control tool for the food industry.

Determination of the Geographical Origin of Coffee Beans Using Terahertz Spectroscopy Combined With Machine Learning Methods

Different geographical origins can lead to great variance in coffee quality, taste, and commercial value. Hence, controlling the authenticity of the origin of coffee beans is of great importance for producers and consumers worldwide. In this study, terahertz (THz) spectroscopy, combined with machine learning methods, was investigated as a fast and non-destructive method to classify the geographic origin of coffee beans, comparing it with the popular machine learning methods, including convolutional neural network (CNN), linear discriminant analysis (LDA), and support vector machine (SVM) to obtain the best model. The curse of dimensionality will cause some classification methods which are struggling to train effective models. Thus, principal component analysis (PCA) and genetic algorithm (GA) were applied for LDA and SVM to create a smaller set of features. The first nine principal components (PCs) with an accumulative contribution rate of 99.9% extracted by PCA and 21 variables selected by GA were the inputs of LDA and SVM models. The results demonstrate that the excellent classification (accuracy was 90% in a prediction set) could be achieved using a CNN method. The results also indicate variable selecting as an important step to create an accurate and robust discrimination model. The performances of LDA and SVM algorithms could be improved with spectral features extracted by PCA and GA. The GA-SVM has achieved 75% accuracy in a prediction set, while the SVM and PCA-SVM have achieved 50 and 65% accuracy, respectively. These results demonstrate that THz spectroscopy, together with machine learning methods, is an effective and satisfactory approach for classifying geographical origins of coffee beans, suggesting the techniques to tap the potential application of deep learning in the authenticity of agricultural products while expanding the application of THz spectroscopy.