Advanced applications of near/mid-infrared (NIR/MIR) imaging spectroscopy for rapid prediction of potato and sweet potato moisture contents

Near-infrared (NIR) and mid-infrared (MIR) hyperspectral techniques in tandem with chemometric analyses were employed for allowing the food industry to monitor moisture content (MC) in potato and sweet potato products during drying. Multivariate models were established by partial least-squares regression (PLSR), support vector machine regression (SVMR), locally weighted partial least square regression (LWPLSR), and back propagation artificial neural network (BPANN) using full spectral ranges of 10372-6105 cm^-1 (Spectral Set ), 3996-600 cm^-1 (Spectral Set ), and 1700-900 cm^-1 (Spectral Set ). Non-linear methods in terms of LWPLSR and BPANN obtained better accuracies than linear models for tuber MC prediction. The overall model accuracy based on the NIR spectra (Spectral Set ) was higher than that of models using the MIR spectra. The highest accuracy (R²P = 0.987, RMSEP = 0.015) was achieved by the NIR-LWPLSR using Spectral Set . The results reveal that hyperspectral techniques have great potential to be used for measurement of tuber MC.