loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
18th International Conference on Pattern Recognition (ICPR'06) Volume 3
Class Separability in Spaces Reduced By Feature Selection
Hong Kong
August 20-August 24
ISBN: 0-7695-2521-0
ASCII Text
x 
 
Erinija Pranckeviciene, TinKam Ho, Ray Somorjai, "Class Separability in Spaces Reduced By Feature Selection," Pattern Recognition, International Conference on, vol. 3, pp. 254-257, 18th International Conference on Pattern Recognition (ICPR'06) Volume 3, 2006.
 
 
BibTex
x
 
@article{ 10.1109/ICPR.2006.365,
author = {Erinija Pranckeviciene and TinKam Ho and Ray Somorjai},
title = {Class Separability in Spaces Reduced By Feature Selection},
journal ={Pattern Recognition, International Conference on},
volume = {3},
year = {2006},
issn = {1051-4651},
pages = {254-257},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICPR.2006.365},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Pattern Recognition, International Conference on
TI - Class Separability in Spaces Reduced By Feature Selection
SN - 1051-4651
SP254
EP257
A1 - Erinija Pranckeviciene,
A1 - TinKam Ho,
A1 - Ray Somorjai,
PY - 2006
KW - null
VL - 3
JA - Pattern Recognition, International Conference on
ER -
 
Erinija Pranckeviciene, Institute for Biodiagnostics, National Research Council Canada
TinKam Ho, Institute for Biodiagnostics, National Research Council Canada
Ray Somorjai, Institute for Biodiagnostics, National Research Council Canada
We investigated the geometrical complexity of several high-dimensional, small sample classification problems and its changes due to two popular feature selection procedures, forward feature selection (FFS) and Linear Programming Support Vector Machine (LPSVM). We found that both procedures are able to transform the problems to spaces of very low dimensionality where class separability is improved over that in the original space. The study shows that geometrical complexities have good potentials for comparing different feature selection methods in aspects relevant to classification accuracy, yet independent of particular classifier choices.
Citation:
Erinija Pranckeviciene, TinKam Ho, Ray Somorjai, "Class Separability in Spaces Reduced By Feature Selection," icpr, vol. 3, pp.254-257, 18th International Conference on Pattern Recognition (ICPR'06) Volume 3, 2006
Usage of this product signifies your acceptance of the Terms of Use.