Non-destructive monitoring of quality attributes kinetics during the drying process: A case study of celeriac slices and the model generalisation in selected commodities

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 g_w 100 g_s^-1) and water activity (a_w, 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 g_w 100 g_s^-1).

Keywords: Gaussian process regression; Hyperspectral imaging; Kinetic models; Method comparison; Optimal wavelengths; Total phenolic compounds.