Comparative efficacy of machine-learning models in prediction of reducing uncertainties in biosurfactant production

Jović, Srđan; Guresic, Dejan; Babincev, Ljiljana М.; Draskovic, Nenad; Dekic, Vidosav

doi:10.1007/s00449-019-02165-y

Cited by 4 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MATLAB is a frequently applied software for building artificial neural networks [35] and machine-learning models [36]. Among the research papers with artificial neural networks both for biosurfactant production and any other fermentation product, usually, only one outcome parameter is investigated [37], and if one would like to predict any additional fermentation result parameter, another ANN is built instead of applying two or more outcome parameters simultaneously [38], like in the case of biosurfactant production with Klebsiella sp.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Modeling the Biosurfactant Fermentation by Geobacillus stearothermophilus DSM2313

Czinkóczky

Németh²

2023

Period. Polytech. Chem. Eng.

View full text Add to dashboard Cite

Biosurfactants are emerging molecules in the 21st century. However, their production intensification is still required for the development of feasible bioprocesses. Therefore, this paper studies a new biosurfactant-producer, namely Geobacillus stearothermophilus DSM2313 during statistical optimization via response surface methodology. After the statistical analysis the optimal pH = 7, glucose = 50 g/L and NH4NO3 = 2 g/L concentrations were determined. The biosurfactant production of the bacteria was predicted by our developed artificial neural network. The optimal harvesting time of the broth and the emulsification index values can be predicted simultaneously with the constructed artificial neural network. The best experiment was also kinetically described, and kinetic constants observed. Surface tension and emulsification activity were measured to characterize the formed products' efficiency. Based on these results, biosurfactants from Geobacillus stearothermophilus DSM2313 can act as bioemulsifier and can be applied for example in microbial enhanced oil recovery.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Modeling the Biosurfactant Fermentation by Geobacillus stearothermophilus DSM2313

Czinkóczky

Németh²

2023

Period. Polytech. Chem. Eng.

View full text Add to dashboard Cite

show abstract

“…MATLAB is a frequently applied software for building ANNs and machine‐learning models 18,19 . Research papers applying ANNs for the prediction of biosurfactant fermentation, generally only estimate one outcome parameter 20 .…”

Section: Introductionmentioning

confidence: 99%

“…14 MATLAB is a frequently applied software for building ANNs and machine-learning models. 18,19 Research papers applying ANNs for the prediction of biosurfactant fermentation, generally only estimate one outcome parameter. 20 For multiple (at least two) parameter predictions, multiple ANN is generally built instead of combining two or more outcome parameters into the same ANN, like in the case of biosurfactant production with Klebsiella sp.…”

mentioning

confidence: 99%

Prediction of surfactin fermentation with Bacillus subtilis DSM10 by response surface methodology optimized artificial neural network

Czinkóczky

Sakiyo

Eszterbauer

et al. 2023

Cell Biochemistry & Function

View full text Add to dashboard Cite

Biosurfactants produced by Bacillus species are an emerging group of surface-active molecules. They have excellent surface tension reducer and high emulsifier properties.Generally, the biosurfactant fermentation leads to a low product concentration. Therefore, our goal was to investigate Bacillus subtilis DSM10 production and improve the biosurfactant content in the broth by media optimization via response surface methodology. The optimal combinations of the investigated factors were determined as the following: pH = 9, glucose = 20 g/L, and NH 4 NO 3 = 2 g/L. Under the optimized conditions, the formed surfactin strain reduced surface tension in the broth by 48% (from 72 to 37 mN/m) and the isolated product by 63% (from 72 to 27 mN/m). An artificial neural network was built based on the results of response surface methodology to predict the product quality and the harvesting time of broth. Thus, finally, the model can predict the final cell and product amount, and even their time course, with around 90% reliability.

show abstract

Multiple feature fusion transformer for modeling penicillin fermentation process with unequal sampling intervals

Sun,

Yan,

Jiang

et al. 2023

Bioprocess Biosyst Eng

View full text Add to dashboard Cite

Comparative efficacy of machine-learning models in prediction of reducing uncertainties in biosurfactant production

Cited by 4 publications

References 14 publications

Modeling the Biosurfactant Fermentation by Geobacillus stearothermophilus DSM2313

Modeling the Biosurfactant Fermentation by Geobacillus stearothermophilus DSM2313

Prediction of surfactin fermentation with Bacillus subtilis DSM10 by response surface methodology optimized artificial neural network

Multiple feature fusion transformer for modeling penicillin fermentation process with unequal sampling intervals

Contact Info

Product

Resources

About