Feature Scoring by Mutual Information for Classification of Mass Spectra

Krier, Catherine;François, Damien;Wertz, Vincent;Verleysen, Michel
(2006) 7th International FLINS Conference on Applied Artificial Intelligence (FLINS 2006) — Location: Genova (Italy) (29.August.2006)

Files

C32-FeatureScoringbyMutualInformationforClassificationofMassSpectra.pdf
  • Restricted Access
  • Adobe PDF
  • 747.73 KB
Request a copy

Details

Authors
Abstract
Selecting relevant features in mass spectra analysis is important both for classification and search for causality. In this paper, it is shown how using mutual information can help answering to both objectives, in a model-free nonlinear way. A combination of ranking and forward selection makes it possible to select several feature groups that may lead to similar classification performances, but that may lead to different results when evaluated from an interpretability perspective.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Krier, C., François, D., Wertz, V., & Verleysen, M. (2006). Feature Scoring by Mutual Information for Classification of Mass Spectra. Proceedings of the 7th International FLINS Conference on Applied Artificial Intelligence (FLINS 2006), 557-564. https://hdl.handle.net/2078.5/254174