Comparative efficacy of machine-learning models in prediction of reducing uncertainties in biosurfactant production
| Autor: | Srdjan Jovic, Dejan Gurešić, Nenad S. Drašković, Ljiljana Babincev, Vidosav Dekic |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
0106 biological sciences
Support Vector Machine Bioengineering Machine learning computer.software_genre Models Biological 01 natural sciences Surface-Active Agents Bacterial isolate 010608 biotechnology Production (economics) Firefly algorithm Bioprocess Mathematics Bacteria 010405 organic chemistry business.industry General Medicine 0104 chemical sciences Support vector machine Bioprocess engineering Artificial intelligence Industrial and production engineering business computer Biotechnology |
| Zdroj: | Bioprocess and Biosystems Engineering. 42:1695-1699 |
| ISSN: | 1615-7605 1615-7591 |
| Popis: | An accurate and reliable forecast of biosurfactant production with minimum error is useful in any bioprocess engineering. Bacterial isolate FKOD36 capable of producing biosurfactant was isolated in this study and pre-inoculums was prepared from the agar slants in a small test tube and incubated at 30 °C for 24 h at 120 rpm. Due to inherent non-linearity characteristics of the data set in a bioprocess, conventional modeling techniques are not adequate for predicting biosurfactant production in a microbiological process. The main contribution of the study was to compare two soft-computing models, i.e., support vector regression (SVR) and support vector regression coupled with firefly algorithm to evaluate the best performance of the two mentioned models. Based on the results it was noted that support vector regression coupled with firefly algorithm performs better compared to the simple SVR. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink