Comparison of optimization approaches (response surface methodology and artificial neural network‐genetic algorithm) for a novel mixed culture approach in soybean meal fermentation

Abstract

AbstractA mixed culture of Bacillus coagulans and Lactobacillus johnsonii is utilized to ferment soybean meal (SBM) and the effects of the fermentation conditions (temperature, time, and initial inoculums level) on the different antioxidative properties are measured. Both response surface methodology (RSM) and artificial neural network (ANN) are applied to the experimental data to suggest a better approach for modeling. It is observed that the fermentation conditions have significant effects on antioxidant activity, and by following a mixed culture approach, these properties can be increased efficiently. Although both ANN and RSM fitted to the experimental data with accuracy, it is evident from root mean squared error, R2, and average absolute deviation values that ANN is superior to RSM when predicting the responses. The results thus point to the advantage of using a properly trained ANN in cases of nonlinear fermentative systems and also for prediction of multiple responses simultaneously.Practical applicationsConversion of low‐cost by‐products into value‐added products has always been the main focus of fermentation industry and currently its scope is being expanded to include the use of probiotics to ferment various by‐products apart from dairy products. SBM is a promising by‐product that has not yet reached its full potential use and should be explored further to widen its range of applications. The purpose to develop optimized fermentation processes needs a suitable mathematical model that has the ability to mimic the complex nonlinearity of mixed culture fermentations without compromising its prediction capabilities. The results of this study will be further used to assess the possibility of development of a fermented‐SBM‐based supplement.