Abstract：
The potential of Visual-NIR hyperspectral imaging (VNIR-HSI, 425-1700 nm) to predict celeriac quality attributes during the drying process was investigated. The HSI-Gaussian Process Regression (GPR) fusion method excellently predicted moisture content (MC, R2 ≈ 1.00, RMSE = 0.77 gw 100 gs-1) and water activity (aw, R2 = 0.98, RMSE = 0.04). Moreover, the rehydration ratio (RR, R2 = 0.89, RMSE = 0.04) and colour indices (R2 = 0.80-0.93, RMSE = 0.17-1.45) were reasonably predicted. However, antioxidant activity (AA) and total phenolic compounds (TPC) were poorly predicted. These results are potentially due to MC variations dominating the NIR region, masking phenolic compounds. Finally, the celeriac-based-trained model was assessed by predicting the MC of apple, cocoyam, and carrot slices. The results were encouraging; however, a GPR model trained on the data of all four commodities was more robust (R2 ≈ 1.00, RMSE = 1-2 gw 100 gs-1).
摘要：
视觉-近红外高光谱成像的潜力(VNIR-HSI，425-1700nm），以预测干燥过程中的芹菜质量属性。HSI-高斯过程回归(GPR)融合方法极好地预测了水分含量(MC，R2≈1.00，RMSE=0.77gw100gs-1)和水活度(aw，R2=0.98，RMSE=0.04）。此外，补液率(RR，合理预测了R2=0.89，RMSE=0.04）和颜色指数（R2=0.80-0.93，RMSE=0.17-1.45）。然而,抗氧化活性（AA）和总酚类化合物（TPC）预测不佳。这些结果可能是由于MC变化主导了NIR区域，掩蔽酚类化合物。最后,通过预测苹果的MC来评估基于芹菜的训练模型，cocoyam,还有胡萝卜片.结果令人鼓舞；然而，在所有四种商品的数据上训练的GPR模型更稳健(R2≈1.00，RMSE=1-2gw100gs-1)。
