Paper Info
Title
On Filtering the Training Prototypes in Nearest Neighbour Classification
Abstract
Filtering (or editing) is mainly effective in improving the classification accuracy of the Nearest Neighbour (NN) rule, and also in reducing its storage and computational requirements. This work reviews some well-known editing algorithms for NN classification and presents alternative approaches based on combining the NN and the Nearest Centroid Neighbourhood of a sample. Finally, an empirical analysis over real data sets is provided.
Year
DOI
Venue
2002
10.1007/3-540-36079-4_21
CCIA
Keywords
Field
DocType
nearest neighbour,training prototypes,computational requirement,nearest centroid neighbourhood,empirical analysis,classification accuracy,nearest neighbour classification,nn classification,well-known editing algorithm,alternative approach
Data mining,Nearest neighbour,Data set,Pattern recognition,Computer science,Computer data storage,Filter (signal processing),Neighbourhood (mathematics),Knowledge extraction,Artificial intelligence,Centroid
Conference
Volume
ISSN
ISBN
2504
0302-9743
3-540-00011-9
Citations 
PageRank 
References 
4
0.51
29
Authors
3
Name
Order
Citations
PageRank
José Salvador Sánchez156531.62
R Barandela255823.46
F J. Ferri329322.43