UNSUPERVISED LEARNING APPROACH TO FEATURE SELECTION IN BIOLOGICAL DATA ANALYSIS

Witold Jacak, Karin Pröll

Research output: Chapter in Book/Report/Conference proceedingsConference contribution

Abstract

In this paper we present a novel method for scoring function specification and feature selection by combining unsupervised learning with supervised cross validation. Unsupervised clustering methods (k-means, one dimensional Kohonen SOM, fuzzy c-means) are used to perform a clustering of object-data for a chosen subset of input features and given number of clusters. The resulting object clusters are compared with the predefined original object classes and a matching factor (score) is calculated. This score is used as criterion function for heuristic sequential feature selection and novel cross selection algorithm.
Original languageEnglish
Title of host publication24th European Modeling and Simulation Symposium, EMSS 2012
Pages232-236
Number of pages5
Publication statusPublished - 2012
EventThe 24th European Modeling & Simulation Symposium (EMSS 2012) - Vienna, Austria
Duration: 19 Sep 201221 Sep 2012
http://www.msc-les.org/conf/EMSS2012/

Publication series

Name24th European Modeling and Simulation Symposium, EMSS 2012

Conference

ConferenceThe 24th European Modeling & Simulation Symposium (EMSS 2012)
CountryAustria
CityVienna
Period19.09.201221.09.2012
Internet address

Keywords

  • classification
  • clustering
  • feature selection
  • k-mean
  • fuzzy c-mean
  • Kohonen SOM
  • MLP
  • Feature selection
  • Classification
  • Clustering
  • Fuzzy c-mean
  • K-mean

Fingerprint Dive into the research topics of 'UNSUPERVISED LEARNING APPROACH TO FEATURE SELECTION IN BIOLOGICAL DATA ANALYSIS'. Together they form a unique fingerprint.

Cite this