Heterogeneous versus Homogeneous Machine Learning Ensembles

Aleksandra Petrakova, Michael Affenzeller, Galina Merkuryeva

Research output: Contribution to journalArticlepeer-review


The research demonstrates efficiency of the heterogeneous model ensemble application for a cancer diagnostic procedure. Machine learning methods used for the ensemble model training are neural networks, random forest, support vector machine and offspring selection genetic algorithm. Training of models and the ensemble design is performed by means of HeuristicLab software. The data used in the research have been provided by the General Hospital of Linz, Austria.
Original languageEnglish
Pages (from-to)135-142
JournalInformation Technology and Management Science
Issue number1
Publication statusPublished - Dec 2015


  • Classification task
  • ensemble modelling
  • machine learning
  • majority voting


Dive into the research topics of 'Heterogeneous versus Homogeneous Machine Learning Ensembles'. Together they form a unique fingerprint.

Cite this