Improving feature selection algorithms using normalised feature histograms

A. P. James, A. K. Maan

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)
30 Downloads (Pure)


The proposed feature selection method builds a histogram of the most stable features from random subsets of a training set and ranks the features based on a classifier based cross-validation. This approach reduces the instability of features obtained by conventional feature selection methods that occur with variation in training data and selection criteria. Classification results on four microarray and three image datasets using three major feature selection criteria and a naive Bayes classifier show considerable improvement over benchmark results.

Original languageEnglish
Pages (from-to)490-491
Number of pages2
JournalElectronics Letters
Issue number8
Publication statusPublished - Apr 14 2011
Externally publishedYes


  • cs.AI
  • cs.CV

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Improving feature selection algorithms using normalised feature histograms'. Together they form a unique fingerprint.

Cite this