Determining the geographical origin and glycogen content of oysters using portable near-infrared spectroscopy: Comparison of classification and regression approaches

Oysters are extensively cultivated worldwide. However, significant variations in chemical composition, quality, and price exist between oysters from different geographical origins. This study employed portable near-infrared spectroscopy in conjunction with chemometric analysis to determine the geographical origin and glycogen content of oysters. Pretreatment methods (multiplicative scattering correction, first derivative, and second derivative) were used to preprocess the raw spectra. Partial least squares discriminant analysis (PLS-DA), orthogonal partial least squares discriminant analysis (OPLS-DA), and support vector machine (SVM) were then adopted to establish the qualitative models. Partial least squares regression (PLSR) and support vector machine regression (SVMR) were compared for predicting the glycogen content. The results revealed that the PLS-DA, OPLS-DA, and SVM models classified the geographical origin of oysters with 100% accuracy. For quantitative analysis, the regression equations displayed high predictive ability. The SVMR model was superior to the PLSR model for glycogen content prediction, with a coefficient of determination of prediction (R²_P) of 0.9253 and a residual prediction deviation (RPD) of 3.62. Therefore, the proposed approach is suitable for the accurate and environmentally friendly determination of the geographical origin and glycogen content of oysters, thus representing an attractive alternative method for the traceability supervision and quantitative analysis of seafood products.