By Topic

One Criterion for the Selection of the Cardinality of Learning Set Used by the Associative Pattern Classifier

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Soria-Alcaraz, J.A. ; Div. de Posgrado e Investig., Leon Inst. of Technol., Leon, Mexico ; Santigo-Montero, R. ; Carpio, M.

The Associative Pattern Classifier (CAP) is a novel approach to solve the pattern classification problem. Recent experiments of the behavior of this classifier in different applications have given encouraging results. Due a this evidence, It has been thinking about the existence of a minimum number for which a higher value of samples used in the learning phase of this classifier brings a very low effect over their classification performance. This paper present an empiric way to obtain this minimum number based in the structure of the used database. this method allows us to define a minimum size for the set used in the learning phase of CAP for which the final classification performance will be reasonably stable, optimizing time and computational resources in the process.

Published in:

Electronics, Robotics and Automotive Mechanics Conference (CERMA), 2010

Date of Conference:

Sept. 28 2010-Oct. 1 2010