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

Abstract

A 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, R 2 , 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.

Effects of Different Forms of Practicing a Sport on Athletes’ Nerve Function

“…"If you want to improve accuracy, must slow down the exchange relationship. [9][10] For a more subjective comparison, the number of neural response errors before and after the two groups of experiments was made into a line graph (Figure 1). It is not difficult to find from Figure 1 that as the difficulty of the reaction type increases, the ratio of the mean error between the experimental group and the control group is getting larger and larger, and the rising trend of the post-test broken line of the control group is much higher than that of the experimental group, finally, there is a clear difference in the latter two.…”

Valorization of Vegetable Food Waste and By-Products Through Fermentation Processes

“…Most of these applications focused on the production of functional ingredients like lactic acid, Polyγ-glutamic acid, bioactive peptides to be reintegrated in the food chain, and other compounds like glycosidases or caproate of industrial interest ( Table 1). Within the genus Bacillus, Bacillus coagulans, Bacillus amyloliquefaciens, Bacillus licheniformis and B. subtilis have been used, alone or together with other bacteria and/or fungi, to ferment products derived from rice, soy, oak, fruit, sorghum (Alexandri et al, 2019;Cole et al, 2019;Jiang et al, 2019;Mukherjee et al, 2019;Orts et al, 2019). Rice bran is an abundant by-product stream generated during rice processing that, after enzymatic hydrolysis, can be fermented by B. coagulans with the aim of producing highly pure (>99%) L-lactic acid.…”

“…Soybean dregs can be transformed using poly-γ-glutamic acid producing stains of B. amyloliquefaciens in feed additives, resulting in fermentation products that could help to improve the growth indicators in animal experiments (Jiang et al, 2019). Soybean meal can be fermented by a mixed culture of B. coagulans and Lactobacillus johnsonii, yielding an improvement of antioxidant properties after fermentation (Mukherjee et al, 2019). Furthermore, B. licheniformis was able to ferment enzymatically hydrolyzed okara (a by-product of soy milk manufacturing) to produce soil biostimulants with higher β-glucosidase, phosphatase and dehydrogenase activities (Orts et al, 2019).…”

“…Some differences in fermentative conditions according to each type of fruit and vegetable by-product assayed were observed ( Figure 1B). Soya by-products (Jiang et al, 2019;Mukherjee et al, 2019;Orts et al, 2019;Taddia et al, 2019) were mostly subjected to solid-state fermentation at 30-47 • C using Aspergillus niger and Bacillus species or yeasts employing lower temperatures (20-28 • C) (Papadaki et al, 2019;Chua and Liu, 2020). Barley bran and brewing waste (Amorim et al, 2019;Marson et al, 2019;Outeiriño et al, 2019;Paz et al, 2019;Pejin et al, 2019;Pontonio et al, 2020) was mostly inoculated with Aspergillus, Trichoderma, and LAB species.…”

“…Similarly, vegetable wastes predominantly fermented by Clostridium kluyveri to obtain caproate were carried out at the highest reaction times in a two-step process comprising 80 h and 70 days (Yu et al, 2019). In this sense, fermentations of soya by-products using B. subtilis (Ruan et al, 2020) and combination of B. coagulans and L. johnsonii (Mukherjee et al, 2019) were performed at prolonged times (>140 h) and high initial pH (6.7-7.0). These processes where differentiated from applications using both Weissella cibaria PEP23F and Saccharomyces cerevisiae AN6Y19 to increase fiber content (+40%) in apple residues (Cantatore et al, 2019) that exhibited low initial pH (4.0), high substrate concentrations and shorter fermentation times (48 h).…”