Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/22637 
Year of Publication: 
2005
Series/Report no.: 
Technical Report No. 2005,44
Publisher: 
Universität Dortmund, Sonderforschungsbereich 475 - Komplexitätsreduktion in Multivariaten Datenstrukturen, Dortmund
Abstract: 
This paper investigates the use of Design of Experiments in observational studies in order to select informative observations and features for classification. D-optimal plans are searched for in existing data and based on these plans the variables most relevant for classification are determined. The adapted models are then compared with respect to their predictive accuracy on an independent test sample. Eight different data sets are investigated by this method.
Subjects: 
D-optimality
Genetic Algorithm
Prototypes
Feature Selection
Document Type: 
Working Paper

Files in This Item:
File
Size
157.72 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.