ABSTRACT
Background In the field of microbial fermentation technology, how to optimize the fermentation conditions is of great crucial for practical applications. Here, we use artificial neural networks (ANNs) and support vector machine (SVM) to offer a series of effective optimization methods for the production of iturin A. The concentration levels of asparagine (Asn), glutamic acid (Glu) and proline (Pro) (mg/L) were set as independent variables, while the iturin A titer (U/mL) was set as dependent variable. General regression neural network (GRNN), multilayer feed-forward neural networks (MLFNs) and the SVM were developed. Comparisons were made among different ANNs and the SVM. Results The GRNN has the lowest RMS error (457.88) and the shortest training time (1 s), with a steady fluctuation during repeated experiments, whereas the MLFNs have comparatively higher RMS errors and longer training times, which have a significant fluctuation with the change of nodes. In terms of the SVM, it also has a relatively low RMS error (466.13), with a short training time (1 s). Conclusion According to the modeling results, the GRNN is considered as the most suitable ANN model for the design of the fed-batch fermentation conditions for the production of iturin A because of its high robustness and precision, and the SVM is also considered as a very suitable alternative model. Under the tolerance of 30%, the prediction accuracies of the GRNN and SVM are both 100% respectively in repeated experiments.
Subject(s)
Peptides, Cyclic , Neural Networks, Computer , Algorithms , Fermentation , Batch Cell Culture Techniques , Support Vector MachineABSTRACT
Objective To optimize the baseline on the trapezoidal cross section of stent wires, so as to reduce the risk of intracranial saccular aneurysm rupture after the implantation of such stents. Methods Thirty-eight trapezoidal cross-section wire stents with different baselines were constructed to establish the finite element models. Numerical simulation by fluid-solid interaction method was conducted to calculate 38 maximum pressure gradients on the aneurysm wall. GRNN (general regression neural network) and GA (genetic algorithm) were used to optimize the baseline on the cross-section of stents with trapezoidal cross-section wire so as to minimize the maximal pressure gradient on the aneurysm wall. Results Compared with the traditional stent with rectangular cross-section wire, the maximal pressure gradient on the a neurysm wall was reduced by 7.86% after the implantation with the optimized stent with trapezoidal cross-section wire. Conclusions The combination of GRNN and GA is an effective approach for stent optimization.