Automated Classification of Bioprocess Based on Optimum Compromise Whitening and Clustering

Chemical and biochemical engineering quarterly

J. Náhlík¹  J. Mareš¹  M. Klimt¹  J. Kukal¹  P. Hrnčiřík¹ 

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

DOI  :  10.15255/CABEQ.2014.2090

来源: Croatian Society of Chemical Engineers

【 摘 要 】

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.

【 授权许可】

Unknown