Cancer profiles by affinity propagation

Ambrogi, Federico and Raimondi, Elena and Soria, Daniele and Boracchi, Patrizia and Biganzoli, Elia M. (2008) Cancer profiles by affinity propagation. In: Seventh International Conference on Machine Learning and Applications, 2008. ICMLA'08., 11-13 Dec. 2008, San Diego, California.

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (79kB) | Preview

Abstract

The affinity propagation algorithm is applied to a problem of breast cancer subtyping using traditional biologic markers. The algorithm provides a procedure to determine the number of profiles to be considered.

A well know breast cancer case series was used to compare the results of the affinity propagation with the results obtained with standard algorithms and indexes for the optimal choice of the number of clusters.

Results from affinity propagation are consistent with the results already obtained having the advantage of providing an indication about the number of clusters.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published in: Seventh International Conference on Machine Learning and Applications, 2008. ICMLA'08. Los Alamitos, Calif. : IEEE, 2008, ISBN 978-0-7695-3495-4, pp. 650-655, doi: 10.1109/ICMLA.2008.110
Schools/Departments: University of Nottingham UK Campus > Faculty of Science > School of Computer Science
Depositing User: Soria, Dr Daniele
Date Deposited: 25 Feb 2015 23:28
Last Modified: 17 Sep 2016 10:13
URI: http://eprints.nottingham.ac.uk/id/eprint/28142

Actions (Archive Staff Only)

Edit View Edit View