Grid search parametric optimization for FT-NIR quantitative analysis of solid soluble content in strawberry samples

Abstract

Grid search technology is proposed to choose the influencing parameters for interval partial least squares (iPLS) and moving window partial least squares (MWPLS) models in the Fourier transform near infrared (FT-NIR) spectrometric quantitative determination of solid soluble content (SSC) in strawberry samples. The objective of grid search is to find out a robust way to ensure that the selected parameters of iPLS and MWPLS would output the informative wavebands leading to improved modeling results. For the improvement of model accuracy, the grid search technique is designed for locating the informative wavebands via influential algorithmic parameters on FT-NIR regions corresponding to different spectral responses of molecule vibration. The commonly used iPLS and MWPLS algorithms are modified in cooperation with the grid search technique, to identify the informative wavebands for the improvement of the model prediction performances. A further integration of the wavebands from different regions could obtain some more accurate models based on the calibrating-validating-testing (CVT) sample division framework. The optimized parameters have the potential to be applied to the development of online and realtime measurement for fruit industry.