Artificial neural network TSR for optimization of actinomycin production
The optimization of industrial fermentation processes, particularly for the production of bioactive compounds like Actinomycin V, is essential for maximizing yield and cost-efficiency. This study introduces a hybrid approach integrating Artificial Neural Networks (ANNs) with the Trees Social Relatio...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
REA Press
2024-03-01
|
| Series: | Big Data and Computing Visions |
| Subjects: | |
| Online Access: | https://www.bidacv.com/article_205624_854f7edf845d7ba3413333f261d08df4.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The optimization of industrial fermentation processes, particularly for the production of bioactive compounds like Actinomycin V, is essential for maximizing yield and cost-efficiency. This study introduces a hybrid approach integrating Artificial Neural Networks (ANNs) with the Trees Social Relations Optimization Algorithm (TSR) to optimize medium composition for the production of Actinomycin V by Streptomyces triostinicus. Traditional optimization techniques, such as Response Surface Methodology (RSM), often fall short of capturing the complex, non-linear interactions between medium components. By contrast, the ANN-TSR hybrid approach leverages the predictive power of neural networks and the robust optimization capabilities of TSR, inspired by the resource-sharing behaviors of tree communities. The study employed a Central Composite Design (CCD) to systematically vary concentrations of key medium components, with experimental data used to train the ANN. The TSR algorithm then iteratively refined the ANN model to identify optimal conditions, significantly increasing Actinomycin V yield from an initial 110 mg/L to 443 mg/L. This fourfold enhancement underscores the potential of combining advanced machine learning techniques with nature-inspired optimization algorithms to optimize complex bioprocesses. The methodology presented here offers a generalizable framework applicable to various industrial bioprocesses. |
|---|---|
| ISSN: | 2783-4956 2821-014X |