Please use this identifier to cite or link to this item: http://hdl.handle.net/10419/22817
Full metadata record
DC FieldValueLanguage
dc.contributor.authorEtschberger, Stefanen_US
dc.contributor.authorHilbert, Andreasen_US
dc.date.accessioned2009-01-29T15:09:28Z-
dc.date.available2009-01-29T15:09:28Z-
dc.date.issued2002en_US
dc.identifier.urihttp://hdl.handle.net/10419/22817-
dc.description.abstractMultidimensional scaling is very common in exploratory data analysis. It is mainlyused to represent sets of objects with respect to their proximities in a low dimensionalEuclidean space. Widely used optimization algorithms try to improve therepresentation via shifting its coordinates in direction of the negative gradient of acorresponding fit function. Depending on the initial configuration, the chosen algorithmand its parameter settings there is a possibility for the algorithm to terminatein a local minimum.This article describes the combination of an evolutionary model with a non-metricgradient solution method to avoid this problem. Furthermore a simulation studycompares the results of the evolutionary approach with one classic solution method.en_US
dc.language.isoengen_US
dc.publisheren_US
dc.relation.ispartofseries|aArbeitspapiere zur mathematischen Wirtschaftsforschung |x181en_US
dc.subject.ddc330en_US
dc.subject.stwHeuristisches Verfahrenen_US
dc.subject.stwMathematische Optimierungen_US
dc.subject.stwTheorieen_US
dc.titleMultidimensional Scaling and Genetic Algorithms : A Solution Approach to Avoid Local Minimaen_US
dc.typeWorking Paperen_US
dc.identifier.ppn379949377en_US
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungen-
dc.identifier.repecRePEc:zbw:augamw:181-

Files in This Item:
File
Size
430.87 kB





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