JOURNAL OF COMPUTERS (JCP)
ISSN : 1796-203X
Volume : 4    Issue : 3    Date : March 2009

Dynamic Modeling of Biotechnical Process Based on Online Support Vector Machine
Xianfang Wang, Zhiyong Du, Jindong Chen, and Feng Pan
Page(s): 251-258
Full Text:
PDF (173 KB)


Abstract
Due to the complexity and high non-linearity of biotechnical process, most simple mathematical
models cannot describe the behavior of biochemistry systems very well. Therefore, dynamic
modeling of biotechnical process is indispensable. Support vector machine (SVM) is a novel
machine learning method, which is powerful for the problem characterized by small sample,
non-linearity, high dimension and local minima, and has high generalization. But currently most
support vector machine regression (SVR) training algorithms are offline, which could not be suit for
time-variant system. So an improved SVM called online support vector machine was presented to
modeling for the dynamic feature of fermentation process. The model based on the modified SVM
was developed and demonstrated using simulation experiments. Some models based on SVM
were also presented. The result shows that the modeling based online SVM is superior to modeling
based on SVW.

Index Terms
dynamic modeling, biotechnical process, online support vector machine, on-line estimation