Feature Variable Selection for Near-Infrared Spectroscopy Based on Simulated Annealing Bee Colony Algorithm

Abstract

Variable selection is an effective method to enhance the modeling performance of near-infrared spectroscopy. Given the promising application prospects of intelligent optimization algorithms in spectral feature variable selection, this article combines the artificial bee colony algorithm with the simulated annealing algorithm to construct a simulated annealing bee colony algorithm (SABC). To explore the feasibility of SABC for spectral variable selection, SABC was applied to construct a partial least squares spectral quantitative detection model for corn stover cellulose and soil organic matter contents. The modeling performance was compared with that of the full spectrum, genetic algorithm, simulated annealing algorithm, and artificial bee colony algorithm; it was found that the model regression precision established by SABC was the best. For the cellulose and organic matter content detection models, the coefficients of determination of the validation set were 0.9433 and 0.9853, with the relative root mean squared error of 1.7901% and 0.8011%, and the residual prediction deviation of 4.1741 and 8.3931, respectively, which could meet the corresponding actual detection needs. SABC adopted the strategy of multiple runs to select the repeated wavelength variables, effectively reduced variable dimensions and model complexity, improved the prediction performance of the regression model, and provided a new approach for building a high-performance near-infrared spectroscopy (NIRS) quantitative calibration model.