Effective Variables Selection in Eggs Freshness Graphically Oriented Local Multivariate Analysis using NIR Spectroscopy

Abstract

In multi-component spectral analysis, informative variables selection is important to get satisfied performance. The present research intends to establish relationship between eggs freshness and NIR spectroscopy, and build a compact and robust calibration model. Graphically-oriented local multivariate calibration modeling procedures were used comparatively to select efficient spectral variables in comparison to the full-spectrum model. Three kinds of methods, which were spectral interval selection, effective coefficient variables selection and genetic algorithm, were used for variable selection. Successive projections algorithm (SPA) showed its superior ability in reducing the complexity of model building. A satisfactory result was achieved while only 8 variables were used. Meanwhile, the optimal performance was obtained with genetic algorithm synergy interval partial least- square (GA-siPLS) by using 9 PCs and 42 variables selected, which resulted in root mean square error value of prediction (RMSEP) value of 3.29. This work indicates that it is feasible to identify egg freshness using NIR spectroscopy combined with graphically-oriented local multivariate analysis, and using variables methods is important to reduce he complexity of model building with fewer spectral variables and improve performance of calibration model. Keywords-Variable selection; Multivariate calibration; Near infrared spectroscopy; Egg freshness