Application of hyperspectral imaging and chemometrics for determining quality and maturity of loquats

Abstract

Color, firmness, soluble solid content, and pH are important indices for assessing the quality and maturity of loquats. To explore the feasibility of rapid and non-destructive determination of loquat quality and maturity, this study utilized hyperspectral imaging combined with chemometrics to predict four quality indices of loquats and discriminate their maturity. Partial least squares regression models were developed using both raw and pre-processed spectral data to determine the optimal pre-processing method of multiple scattering correction and standard normal variate (SNV). The competitive adaptive reweighted sampling (CARS) and successive projection algorithms were used to extract spectral features. Feature wavelength models were subsequently developed using multiple linear regression (MLR) and error back propagation neural network. Finally, maturity determination models for loquats were developed by partial least squares discrimination analysis (PLS-DA), support vector machine, and random forest. The SNV-CARS-MLR model performed relatively better than the other models for predicting four quality indices. The PLS-DA model exhibited superior performance, with discrimination accuracies of 99.19% and 96.67% for the calibration and prediction sets. This study demonstrates that integrating hyperspectral imaging and chemometrics enables rapid and non-destructive determination of loquat quality and maturity.