LC: A Conceptual Clustering Algorithm

Authors:
José Francisco Martínez Trinidad;Guillermo Sánchez-Díaz
Affiliations:
-;-
Venue:
MLDM '01 Proceedings of the Second International Workshop on Machine Learning and Data Mining in Pattern Recognition
Year:
2001

Citing 4
Cited 0

Determining the feature relevance for non-classically described objects and a new algorithm to compute typical fuzzy testors

Pattern Recognition Letters
A conceptual version of the K-means algorithm

Pattern Recognition Letters
Conceptual Clustering, Categorization, and Polymorphy

Machine Learning
Structuralization of universes

Fuzzy Sets and Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

An algorithm for automated construction of conceptual classification is presented. The algorithm arranges the objects into clusters using clustering criterion based on graph theory and constructs the concepts based on attributes that distinguish objects in the different computed clusters (typical testors). The algorithm may be applied in problems where the objects can be described simultaneously by qualitative and quantitative attributes (mixed data); with incomplete descriptions (missing data) and the number of clusters to be formed is not known a priori. LC has been tested on data from standard public databases.