We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Model penicillin fermentation by least squares support vector machine with tuning based on amended harmony search.
- Authors
Ou Yang, Hai-Bin; Li, Steven; Zhang, Ping; Kong, Xiangyong
- Abstract
Penicillin fermentation is an important part of microbial fermentation. Due to the existence of error date in the independent variables and dependent variables of the penicillin fermentation sample data, the accuracy of the model of penicillin fermentation is affected. In this paper, an amended harmony search (AHS) algorithm is developed to adjust the hyper-parameters of least squares support vector machine (LS-SVM) in order to build penicillin fermentation process model with prediction accuracy. The AHS algorithm is investigated by unconstrained benchmark functions with different characteristics. Compared with other several optimization approaches, AHS demonstrates a better performance. Moreover, using the simulation data from the PenSim simulation platform to validate the effectiveness of the penicillin fermentation process modeling, experiment results show that the penicillin fermentation process modeling based on the tuned LS-SVM by AHS possesses robustness and generalization ability.
- Subjects
BETA lactam antibiotics; MICROBIOLOGICAL synthesis; ANTIBACTERIAL agents; ISOTONIC regression; VARIANCE inflation factors (Statistics); PENICILLIN; ALGORITHMS; ROBUST control; EDUCATION; THERAPEUTICS
- Publication
International Journal of Biomathematics, 2015, Vol 8, Issue 3, p-1
- ISSN
1793-5245
- Publication type
Article
- DOI
10.1142/S1793524515500370