Search

The traditional quality testing methods of Baijiu have several challenges including long duration of testing that increases the workload of the laboratory. In this experiment, Raman spectroscopy was used to efficiently control the quality of Baijiu. The spectroscopy were primarily preprocessed using the wavelet domain denoising technique and the principal component analysis (PCA). The rapid identification and classification of 496 samples of Baijiu with various alcohol concentrations (AC), flavor grade (FG), and production year (PY) were achieved using a neural network model constructed based on Raman spectroscopy and genetic algorithm-back propagation (GA-BP). The results indicated that in comparison to the BP neural network, the best GA-BP network model achieved 95.68%, 91.37%, and 93.96% correct recognition rates for the three indicators namely, AC, FG, and PY respectively. Additionally, the average correct recognition rate of the model was enhanced by 3.62%, 9.4%, and 8.45% for AC, FG, and PY respectively. In this study, for the first time, AC, FG, and PY of Baijiu were combined to construct a model that enabled the scientific identification of Baijiu samples in unique circumstances and it also provided a new reference method for the identification, detection, and classification of Baijiu. [Display omitted] ● Prediction of alcohol concentration, flavor grade and production year of Baijiu. ● Spectral preprocessing using wavelet denoising and principal component analysis. ● Baijiu was identified by combining Raman spectroscopy with GA-BP neural network. [ABSTRACT FROM AUTHOR]

Drying is an important process in black tea processing, at the same time, catechin is an important factor in determining the sensory quality of black tea. However, there is a lack of effective real-time detection methods for the detection of catechins in black tea drying process. Therefore, we analyzed the trends of catechins in black tea drying process under different drying conditions and further explored the quantitative prediction model of eight individual catechins in black tea drying process by Least squares support vector machine (LS-SVM) based on near-infrared spectroscopy (NIRS) and chemometrics methods. The results showed that the prediction accuracy of the eight monomeric catechins prediction models established based on the extraction of competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) feature spectra achieved the best results, and the correlation coefficient values of the prediction sets (R p) were all greater than 0.98, and the relative percentage deviation (RPD) values were all greater than 5. The gallocatechin gallate (GCG) with the highest prediction accuracy was 0.9977 and the RPD value was 14.8. This study shows that the method based on near-infrared spectroscopy and chemometrics has strong predictive power for catechins in black tea drying process, which is a guideline for controlling the sensory quality of black tea drying. • Different drying temperatures and times affect the catechin content of black tea. • Catechin during black tea drying was monitored using NIR spectroscopy. • Different quantitative prediction models were compared to accurate detection of catechins. • NIR spectroscopy can be used to monitor the drying process of black tea. [ABSTRACT FROM AUTHOR]