DocumentCode :
919987
Title :
Convergence of the edited nearest neighbor (Corresp.)
Author :
Wagner, T.J.
Volume :
19
Issue :
5
fYear :
1973
fDate :
9/1/1973 12:00:00 AM
Firstpage :
696
Lastpage :
697
Abstract :
The edited 
nearest neighbor rule ( -NNR) consists of 1) eliminating those samples from the data which are not classified correctly by the -NNR and the remainder of the data, and 2) using the NNR with the samples which remain from 1) to classify new observations. Wilson has shown that this rule has an asymptotic probability of error which is better than that of the -NNR. A key step in his development is showing the convergence of the edited nearest neighbor. His lengthy argument is replaced here by a somewhat simpler one which uses an intuitive fact about the editing procedure.
nearest neighbor rule ( -NNR) consists of 1) eliminating those samples from the data which are not classified correctly by the -NNR and the remainder of the data, and 2) using the NNR with the samples which remain from 1) to classify new observations. Wilson has shown that this rule has an asymptotic probability of error which is better than that of the -NNR. A key step in his development is showing the convergence of the edited nearest neighbor. His lengthy argument is replaced here by a somewhat simpler one which uses an intuitive fact about the editing procedure.Keywords :
Pattern classification; Convergence; Equations; Filtering; Frequency; Nearest neighbor searches; Random variables;
fLanguage :
English
Journal_Title :
Information Theory, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9448
Type :
jour
DOI :
10.1109/TIT.1973.1055059
Filename :
1055059
Link To Document :
