A Fuzzy Optimization Strategy for the Implementation of RBF LSSVR Model in Vis–NIR Analysis of Pomelo Maturity

Spectral analysis is a practical technology used for rapid analysis of fruit maturity. Least-squares support vector regression (LSSVR) with radial basis function (RBF) kernel is an effective nonlinear method for the quantitative calibration in the visible-near-infrared (Vis-NIR) spectral region. However, the nonlinear effect and high-dimensional spectrum data influence the prediction accuracy and complexity of modeling procedures. This article presents a fuzzy optimization strategy to improve the performance of the RBF LSSVR model in Vis-NIR quantitative determination of pomelo maturity. In the proposed strategy, a linguistic iterative mode is introduced for optimizing RBF kernel parameters. The input variables of the model are the informative features extracted through fuzzy transform principal component analysis algorithm, and the output was a polynomial equation of the inputs. In this article, pomelo maturity is recorded using the quantitative indices of L*, a*, and b*. The Vis-NIR spectral data of Pomelo samples are first converted to a set of fuzzy-transformed principal components and inputted into a fuzzy-optimized LSSVR model for calibration, validation, and test. Parameter uncertainty is evaluated to verify the effectiveness of the proposed strategy. Experimental results show that the proposed fuzzy optimization strategy is feasible for reducing the computational complexity of the BRF LSSVR model, and the predictions on L*, a*, and b* are much appreciable. The proposed fuzzy optimization strategy based on the linguistic iteration mode is considered as the effective implementation for calibration models in the spectroscopy technology for rapid prediction of fruit maturity.