The alpha-procedure: A nonparametric invariant method for automatic classification of multi-dimensional objects

Tatjana Lange, Pavlo Mozharovskyi

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A procedure, called α-procedure, for the efficient automatic classification of multivariate data is described. It is based on a geometric representation of two learning classes in a proper multi-dimensional rectifying feature space and the stepwise construction of a separating hyperplane in that space. The dimension of the space, i.e. the number of features that is necessary for a successful classification, is determined step by step using two-dimensional repères (linear subspaces). In each step a repère and a feature are constructed in a way that they yield maximum discriminating power. Throughout the procedure the invariant, which is the object’s affiliation with a class, is preserved.

Original languageEnglish
Title of host publicationData Analysis, Machine Learning and Knowledge Discovery
EditorsLars Schmidt-Thieme, Ruth Janning, Myra Spiliopoulou
PublisherKluwer Academic Publishers
Pages79-86
Number of pages8
ISBN (Print)9783319015941
DOIs
Publication statusPublished - 1 Jan 2014
Externally publishedYes
Event36th Annual Conference of the German Classification Society on Data Analysis, Machine Learning and Knowledge Discovery, GfKl 2012 - Hildesheim, Germany
Duration: 1 Aug 20123 Aug 2012

Publication series

NameStudies in Classification, Data Analysis, and Knowledge Organization
Volume47
ISSN (Print)1431-8814

Conference

Conference36th Annual Conference of the German Classification Society on Data Analysis, Machine Learning and Knowledge Discovery, GfKl 2012
Country/TerritoryGermany
CityHildesheim
Period1/08/123/08/12

Fingerprint

Dive into the research topics of 'The alpha-procedure: A nonparametric invariant method for automatic classification of multi-dimensional objects'. Together they form a unique fingerprint.

Cite this