Improved prediction of vitamin C and reducing sugar content in sweetpotatoes using hyperspectral imaging and LARS-enhanced LASSO variable selection
作者：Hong-Ju He, Chen Zhang, Xihui Bian, Jinliang An, Yuling Wang, Xingqi Ou, Mohammed Kamruzzaman*
关键字：Variable selection, LARS-LASSO, Hyperspectral data, Sweet potato roots, Reducing sugar, Vitamin C
论文来源：期刊
具体来源：Journal of Food Composition and Analysis, 2024, 132, 106350
发表时间：2024年
This study utilized least angle regression (LARS) with the least absolute shrinkage and selection operator (LASSO) to select important wavelengths for rapid quantification of vitamin C (V-c) and reducing sugar (RS) in sweetpotato roots (SPR) using hyperspectral imaging (900-1700 nm). Nine wavelengths strongly correlated with V-c levels and twelve with RS were identified, achieving good predictions with partial least squares (PLS) regression (V-c: r(P) = 0.9704, RMSEP = 1.0098 mg/100 g; RS: r(P) = 0.9641, RMSEP = 0.2725 g/100 g). Validation with an independent sample set (n = 35) showed minimal deviation between predicted and actual values (V-c: 1.179-1.211 mg/100 g; RS: 0.316-0.324 g/100 g). Explainable AI and SHapley Additive exPlanations (SHAP) values were used to interpret the selected wavelengths. Chemical maps visually analyzed V-c and RS distribution in different SPR samples. This method effectively estimates V-c and RS levels in SPR, potentially aiding SPR quality assessment during post-harvest marketing and storage.