Advertisement

Neuroinformatics

, Volume 10, Issue 4, pp 409–413 | Cite as

A WEKA Interface for fMRI Data

  • M. Pyka
  • A. Balz
  • A. Jansen
  • A. Krug
  • E. Hüllermeier
News Item

Originated as a sub-discipline in artificial intelligence, machine learning has evolved into an independent field used by researchers from various scientific disciplines to solve classification and prediction problems in their area. In neuroimaging, machine learning approaches have become popular tools to predict cognitive states or group membership of subjects from functional and structural magnetic resonance imaging (MRI) data. As opposed to univariate analyses, pattern classifiers are considered to be more sensitive for discriminating information in neuroimage data since areas that are of particular importance for the classification process do not have to reflect necessarily a selective hemodynamic increase or decrease. Rather, they represent a multivariate pattern that leads, in conjunction with other areas, to high predictability. This multivariate nature of machine learning approaches leads in neuroimaging to increased sensitivity over univariate methods and allows...

Keywords

fMRI WEKA Machine learning Pattern recognition 

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  • M. Pyka
    • 1
  • A. Balz
    • 2
  • A. Jansen
    • 1
  • A. Krug
    • 1
  • E. Hüllermeier
    • 2
  1. 1.Department of PsychiatryPhilipps-Universität MarburgMarburgGermany
  2. 2.Department of Mathematics and Computer SciencePhilipps-Universität MarburgMarburgGermany

Personalised recommendations