Towards a Fuzzy Extension of the López de Mántaras Distance
In this paper we introduce FLM, a divergence measure to compare a fuzzy and a crisp partition. This measure is an extension of LM, the López de Mántaras distance. This extension allows to handle domain objects having attributes with continuous values. This means that for some domains the use of fuzzy sets may report better results than the discretization that is the usual way to deal with continuous values. We experimented with both FLM and LM in the context of the lazy learning method called Lazy Induction of Descriptions useful for classification tasks.
KeywordsMachine learning partitions fuzzy partitions entropy measures López de Mántaras distance
Unable to display preview. Download preview PDF.
- 3.Quinlan, J.R.: Induction of decision trees. Machine Learning 1, 81–106 (1986)Google Scholar
- 6.Armengol, E., Puig, S.: Combining two lazy learning methods for classification and knowledge discovery. a case study for malignant melanoma diagnosis. In: Proceedings of the International Conference on Knowledge Discovery and Information Retrieval, pp. 200–207 (2011)Google Scholar
- 10.Hüllermeier, E., Rifqi, M.: A fuzzy variant of the Rand index for comparing clustering structures. In: Proceedings of IFSA/EUSFLAT Conference, pp. 1294–1298 (2009)Google Scholar
- 12.Zimmermann, H.: Fuzzy Set Theory and its applications, 2nd edn. Kluver Academic Publishers (1992)Google Scholar
- 13.Asuncion, A., Newman, D.J.: UCI machine learning repository (2007)Google Scholar
- 14.Witten, I., Frank, E., Trigg, L., Hall, M., Holmes, G., Cunningham, S.: Weka: Practical machine learning tools and techniques with java implementations (1999)Google Scholar