Original scientific paper

https://doi.org/10.15255/CABEQ.2014.2090

Automated Classification of Bioprocess Based on Optimum Compromise Whitening and Clustering

J. Kukal ; Faculty of Chemical Engineering, University of Chemical Technology in Prague, Technicka 5, 166 28 Prague 6, Czech Republic
J. Mareš ; Faculty of Chemical Engineering, University of Chemical Technology in Prague, Technicka 5, 166 28 Prague 6, Czech Republic
J. Náhlík ; Faculty of Chemical Engineering, University of Chemical Technology in Prague, Technicka 5, 166 28 Prague 6, Czech Republic
P. Hrnčiřík ; Faculty of Chemical Engineering, University of Chemical Technology in Prague, Technicka 5, 166 28 Prague 6, Czech Republic
M. Klimt ; Faculty of Chemical Engineering, University of Chemical Technology in Prague, Technicka 5, 166 28 Prague 6, Czech Republic

Abstract

The proposed methodology of technological state classification is based on data smoothing, dimensionality reduction, compromise whitening, and optimum clustering. The novelty of our approach is in the stabile state hypothesis which improves initialization of c-mean algorithm and enables interleaved cross-validation strategy. We also employ the Akaike information criterion to obtain the optimum number of technological
states that minimize it, but using as many as possible clusters and components. The general approach is applied to state classification of Pseudomonas putida fed-batch cultivation on octanoic acid.

Keywords

fed-batch cultivation; technological state classification; dimensionality reduction; clustering; stabile state hypothesis

Hrčak ID:

150644

URI

https://hrcak.srce.hr/150644

Publication date:

3.1.2016.

Visits: 1.338 *