Advanced search
1 file | 498.86 KB

Inducing decision trees via concept lattices

Author
Organization
Abstract
We present a novel method for the construction of decision trees. The method utilises concept lattices in that certain formal concepts of the concept lattice associated to input data are used as nodes of the decision tree constructed from the data. The concept lattice provides global information about natural clusters in the input data, which we use for selection of splitting attributes. The usage of such global information is the main novelty of our approach. Experimental evaluation indicates good performance of our method. We describe the method, experimental results, and a comparison with standard methods on benchmark datasets.
Keywords
concept lattice, machine learning, classification, formal concept analysis, decision trees

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 498.86 KB

Citation

Please use this url to cite or link to this publication:

Chicago
Belohlavek, Radim, Bernard De Baets, Jan Outrata, and Vilem Vychodil. 2009. “Inducing Decision Trees via Concept Lattices.” International Journal of General Systems 38 (4): 455–467.
APA
Belohlavek, R., De Baets, B., Outrata, J., & Vychodil, V. (2009). Inducing decision trees via concept lattices. INTERNATIONAL JOURNAL OF GENERAL SYSTEMS, 38(4), 455–467. Presented at the 5th International conference on Concept Lattices and Their Applications.
Vancouver
1.
Belohlavek R, De Baets B, Outrata J, Vychodil V. Inducing decision trees via concept lattices. INTERNATIONAL JOURNAL OF GENERAL SYSTEMS. 2009;38(4):455–67.
MLA
Belohlavek, Radim et al. “Inducing Decision Trees via Concept Lattices.” INTERNATIONAL JOURNAL OF GENERAL SYSTEMS 38.4 (2009): 455–467. Print.
@article{692668,
  abstract     = {We present a novel method for the construction of decision trees. The method utilises concept lattices in that certain formal concepts of the concept lattice associated to input data are used as nodes of the decision tree constructed from the data. The concept lattice provides global information about natural clusters in the input data, which we use for selection of splitting attributes. The usage of such global information is the main novelty of our approach. Experimental evaluation indicates good performance of our method. We describe the method, experimental results, and a comparison with standard methods on benchmark datasets.},
  author       = {Belohlavek, Radim and De Baets, Bernard and Outrata, Jan and Vychodil, Vilem},
  issn         = {0308-1079},
  journal      = {INTERNATIONAL JOURNAL OF GENERAL SYSTEMS},
  language     = {eng},
  location     = {Montpellier, France},
  number       = {4},
  pages        = {455--467},
  title        = {Inducing decision trees via concept lattices},
  url          = {http://dx.doi.org/10.1080/03081070902857563},
  volume       = {38},
  year         = {2009},
}

Altmetric
View in Altmetric
Web of Science
Times cited: