STOCHASTIC COMPLEXITY AS A TAXONOMIC TOOL

Authors
GYLLENBERG HG GYLLENBERG M KOSKI T LUND T
Citation
Hg. Gyllenberg et al., STOCHASTIC COMPLEXITY AS A TAXONOMIC TOOL, Computer methods and programs in biomedicine, 56(1), 1998, pp. 11-22
Citations number
15
Categorie Soggetti
Computer Science Interdisciplinary Applications","Computer Science Theory & Methods","Computer Science Interdisciplinary Applications","Engineering, Biomedical","Medical Informatics","Computer Science Theory & Methods
Journal title
Computer methods and programs in biomedicine → ACNP
ISSN journal
01692607
Volume
56
Issue
1
Year of publication
1998
Pages
11 - 22
Database
ISI
SICI code
0169-2607(1998)56:1<11:SCAATT>2.0.ZU;2-U
Abstract
In this paper we propose a method of constructing a hierarchial classi fication based on the notion of stochastic complexity. Minimization of stochastic complexity amounts to maximization of the information cont ent of the classification. A dendrogram is obtained by first finding t he classification which minimizes stochastic complexity and then by st ep-wise merging of groups such that at each step there is a minimum lo ss of information. The method was applied to a database containing 531 3 strains of Enterobacteriaceae. The results are in reasonable accorda nce with present-day views on the taxonomy of Enterobacteriaceae. (C) 1998 Elsevier Science Ireland Ltd. All rights reserved.