By Topic

Classification performance on a population with contexts

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
$33 $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

4 Author(s)
Ashish Choudhary ; Translational Genomics Research Institute, 445 N. Fifth Street, Suite 600, Phoenix, AZ 85004, USA ; Jianping Hua ; Michael L. Bittner ; Edward R. Dougherty

Several classification studies have been conducted to relate molecular expression to disease progression, outcome and vulnerability. These studies have failed except in simple situations. A reason for this has been that classification schemes have in general ignored the heterogeneity of underlying cellular contexts. In this work we conduct a model based study to demonstrate and quantify how existence of contexts degrades classification performance.

Published in:

2008 IEEE International Workshop on Genomic Signal Processing and Statistics

Date of Conference:

8-10 June 2008