Classification of Chinese traditional cereal vinegars and antioxidant property predication by fluorescence spectroscopy

In this work, a rapid and accurate strategy for classification of Chinese traditional cereal vinegars (CTCV) and antioxidant property predication was proposed by using the combination fluorescence spectroscopy and machine learning. Three characteristic fluorescent components were extracted by parallel factor analysis (PARAFAC), which have correlations greater than 0.8 with antioxidant activity of CTCV obtained by Pearson correlation analysis. Machine learning methods, including linear discriminant analysis (LDA), partial least squares-discriminant analysis (PLS-DA) and N-way partial least squares discriminant analysis (N-PLS-DA), were used for the classification of different types of CTCV, and the correct classification rates was higher than 97%. The antioxidant property of CTCV were further quantified by using optimized variable-weighted least-squares support vector machine based on particle swarm optimization (PSO-VWLS-SVM). The proposed strategy provides a basis for further research on antioxidant active ingredients and antioxidant mechanisms of CTCV, and enable the continued exploration and application of CTCV from different types.