Evaluation of breast cancer tumor classification with unconstrained functional networks classifier

  • Emad A. El-Sebakhy*
  • , Kanaan Abed Faisal
  • , T. Helmy
  • , F. Azzedin
  • , A. Al-Suhaim
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

23 Scopus citations

Abstract

This paper proposes functional networks as an unconstrained classifier scheme for multivariate data to diagnose the breast cancer tumor. The performance of this new technique is measured using two well known databases under the minimum description length criterion, the results are compared with the most common existing classifiers in both computer science and statistics literatures. This new classifier shown reliable and efficient results with better correct classification rate, and much less computational time.

Original languageEnglish
Title of host publicationIEEE International Conference on Computer Systems and Applications, 2006
PublisherIEEE Computer Society
Pages281-287
Number of pages7
ISBN (Print)1424402123, 9781424402120
DOIs
StatePublished - 2006

Publication series

NameIEEE International Conference on Computer Systems and Applications, 2006
Volume2006

Keywords

  • Breast cancer detection
  • Functional networks
  • Minimum description length
  • Pattern classification

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Evaluation of breast cancer tumor classification with unconstrained functional networks classifier'. Together they form a unique fingerprint.

Cite this