Detection of parameters in solid state fermentation of Monascus by near infrared spectroscopy

Abstract

The prediction model was constructed using the near-infrared spectroscopy combined with the interval least squares support vector machine method (siLS-SVM) of moisture content and pH value change during the solid fermentation of Monascus. The predictive model was established with partial least squares regression (PLS), and the comprehensive performance of the model was evaluated by cross-validating the mean square error, absolute error value and relative error value. The findings suggest that the LS-SVM model established by siLS-SVM algorithm owns superior predictability and stability for the changes of water content and pH value in the solid fermentation of Monascus (the average relative error is 1.52% and 1.55%, respectively), which can be used for the accurate quantitative prediction. The results showed that near infrared spectroscopy could be used for rapid and non-destructive determination of water content and PH value in solid-state fermentation of Monascus, which provided a new way for optimization of solid-state fermentation process of Monascus under bran substrate.