Near infrared spectroscopy wavelength selection method and the application based on synergy interval Gaussian process

Abstract

Based on Gaussian Process (GP), a wavelength selection algorithm named Synergy Interval Gaussian Process (siGP) model is proposed in this paper by using near infrared spectroscopy technology. Full spectrum is divided into a series of unique and equal spacing intervals, before selecting optimal several intervals to establish GP model. Due to the GP model with nonlinear processing ability, the method reduces the disadvantages of nonlinear factor. Taking the near infrared spectrum data of moisture content and pH in solid-state fermentation of monascus as performance verification object of this new algorithm, the prediction correlation coefficient (R p ) of moisture content and pH are 0.956 4 and 0.977 3, respectively. The root mean square errors for prediction set (RMSEP) are 0.012 7 and 0.161 0, respectively. Data points participating in modeling decrease respectively from the original 1 500 to 225 and 375. In the prediction for independent samples, it shows good accuracy. Comparing with traditional synergy interval partial least squares (siPLS) algorithm, the results show that the siGP achieves the best prediction result. The prediction correlation coefficient of moisture content and pH in new algorithm has increased respectively by 3.37% and 3.51% under the model of Gaussian Process, with increases of 29.4% and 34.8% in the root mean square errors for prediction set. This study shows that the combination of siGP and GP model can select wavelength effectively and improves the prediction accuracy of the NIR model. This method is reference for realizing the online detection and optimization control.