Neural networks applied to the prediction of fed-batch fermentation kinetics of Bacillus thuringiensis

Abstract

This paper proposes using a new recurrent neural network model (RNNM) to predict and control fed batch fermentations of Bacillus thuringiensis. The control variables are the limiting substrate and the feeding conditions. The multi-input multi-output RNNM proposed has twelve inputs, seven outputs, nineteen neurons in the hidden layer, and global and local feedbacks. The weight update learning algorithm designed is a version of the well known backpropagation through time algorithm directed to the RNNM learning. The error approximation for the last epoch of learning is 2% and the total learning time is 51 epochs, where the size of an epoch is 162 iterations. The RNNM generalization was carried out reproducing a B. thuringiensis fermentation not included in the learning process. It attains an error approximation of 1.8%.

Artificial Neural Network-Genetic Algorithm Approach to Optimize Media Constituents for Enhancing Lipase Production by a Soil Microorganism

“…The model was trained and tested adequately with the experimental data, and evaluated by the R 2 value obtained, which was found to be about 0.99. Valdez-Castro et al reported that ANN based model was able to predict the fed-batch fermentation kinetics of Bacillus thuringiensis [3] based on similar ANN modeling procedure. The ANN model for lipolytic activities of the culture is presented in Table 4.…”

“…To avoid any convergence to local maxima, point mutations were used, which help in introducing diversity in the population and therefore force the algorithm to search for entire space. The crossover and mutation probabilities were assigned to be 0.9 and 0.05, respectively [3]. The offspring generated were evaluated of their fitness using the ANN model developed.…”

“…Artificial neural networks (ANN) are gaining importance in modeling of complex biological systems due to its excellent performance in pattern recognition, and in the modeling of nonlinear relationships involving a multitude of variables in place of conventional and statistical techniques [3,4].…”

Review of advanced physical and data‐driven models for dynamic bioprocess simulation: Case study of algae–bacteria consortium wastewater treatment

“…To apply to a dynamic system, an ANN is designed by feeding the system's current states to predict future ones at the next time step. Another approach is to use Recurrent Neural Networks, which is structured specifically to model time-series events (Valdez-Castro, Baruch, & Barrera-Cortés, 2003). Another approach is to use Recurrent Neural Networks, which is structured specifically to model time-series events (Valdez-Castro, Baruch, & Barrera-Cortés, 2003).…”

Hybrid physics‐based and data‐driven modeling for bioprocess online simulation and optimization

“…Given the large size of accumulated data, models based on machine learning, particularly artificial neural networks, have been adopted to simulate bacterial fermentation and algal photo-production (del Dineshkumar et al, 2015). Other advanced neural networks such as recurrent and convolutional neural networks have also been used to simulate the production of different biochemical (Valdez-Castro et al, 2003;. Moreover, through the use of stochastic optimization, data-driven models have been adopted to optimize long-term fed-batch processes, causing considerable increases in production of different metabolites and yielding highest intracellular contents of bioproducts reported to date (del Rio-Chanona, Manirafasha, Zhang, Yue, & Jing, 2016;Dineshkumar et al, 2015).…”