Qualitative Prediction of Yeast Growth Process Based on Near Infrared Spectroscopy

To improve the yield of industrial fermentation, this study presented a method based on near infrared spectroscopy to predict the growth process of yeast. The spectral data were measured from fermentation sample by Fourier-transform near-infrared (FT-NIR) spectrometer in the process of yeast culture. Each spectrum was acquired over the range of 10000 to 4000 cm(-1). Meanwhile, the optical density (OD) values of fermentation sample were determined with photoelectric turbidity method. A method on the basis of competitive adaptive reweighted sampling (CARS) was used to select characteristic wavelength variables of NIR data, and then extreme learning machine (ELM) algorithm was employed to develop the categorization model about the four growth phases of yeast. The experimental results showed that only 30 characteristic wavelength variables of NIR data were selected by CRAS algorithms, and prediction accuracy of the training set and testing set of the CARS-ELM model was 98.68% and 97.37%, respectively. This study showed that near infrared spectral analysis technique was feasible to predict the growth process of yeast.