Conference Papers Year : 2017

Periodic split method: learning more readable decision trees for human activities

Matthieu Boussard
  • Function : Author
Clodéric Mars
  • Function : Author
Rémi Dès
  • Function : Author
Caroline Chopinaud
  • Function : Author

Abstract

Placing your trust in algorithms is a major issue in society today. This article introduces a novel split method for decision tree generation algorithms aimed at improving the quality/readability ratio of generated decision trees. We focus on human activities learning that allow the definition of new temporal features. By virtue of these features, we present here the periodic split method, which produces similar or superior quality trees with reduced tree depth.
Fichier principal
Vignette du fichier
APIA_2017_paper_18.pdf (1) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01561514 , version 1 (12-07-2017)

Identifiers

  • HAL Id : hal-01561514 , version 1

Cite

Matthieu Boussard, Clodéric Mars, Rémi Dès, Caroline Chopinaud. Periodic split method: learning more readable decision trees for human activities . Conférence Nationale sur les Applications Pratiques de l’Intelligence Artificielle, Jul 2017, Caen, France. ⟨hal-01561514⟩

Collections

APIA2017
787 View
284 Download

Share

More