Classification of Multivariate Data Using Distribution Mapping Exponent

0405144 - UIVT-O 20030135 RIV HU eng C - Conference Paper (international conference)
Jiřina, Marcel
Classification of Multivariate Data Using Distribution Mapping Exponent.
Proceedings of the International Conference in Memoriam John von Neumann. Budapest: Budapest Muszaki Foiskola (Budapest Polytechnic), 2003 - (Szakál, A.), s. 155-168. ISBN 963-7154-21-3.
[International Conference in Memorial John von Neumann. Budapest (HU), 12.12.2003]
R&D Projects: GA MŠMT LN00B096
Keywords : multivariate data * classification * distribution mapping exponent
Subject RIV: BA - General Mathematics

We introduce distribution-mapping exponent that is something like effective dimensionality of multidimensional space. The method for classification of multivariate data is based on local estimate of distribution mapping exponent q for each point x. It is shown that the sum of reciprocals of q-th power of distances of all points of a given class can be used as the probability density estimate.
Permanent Link: http://hdl.handle.net/11104/0125346