ON THE REDUCTION OF THE NEAREST-NEIGHBOR VARIATION FOR MORE ACCURATE CLASSIFICATION AND ERROR-ESTIMATES

Authors
DJOUADI A
Citation
A. Djouadi, ON THE REDUCTION OF THE NEAREST-NEIGHBOR VARIATION FOR MORE ACCURATE CLASSIFICATION AND ERROR-ESTIMATES, IEEE transactions on pattern analysis and machine intelligence, 20(5), 1998, pp. 567-571
Citations number
8
Categorie Soggetti
Computer Science Artificial Intelligence","Computer Science Artificial Intelligence","Engineering, Eletrical & Electronic
Journal title
IEEE transactions on pattern analysis and machine intelligence → ACNP
ISSN journal
01628828
Volume
20
Issue
5
Year of publication
1998
Pages
567 - 571
Database
ISI
SICI code
0162-8828(1998)20:5<567:OTROTN>2.0.ZU;2-1
Abstract
In designing the nearest-neighbor (NN) classifier, a method is present ed to produce a finite sample size risk close to the asymptotic one. I t is based on an attempt to eliminate the first-order effects of the s ample size, as well as all higher odd terms. This method uses the 2-NN rule without the rejection option and utilizes a polarization scheme. Simulation results are included as a means of verifying this analysis .