Automatic aspect discrimination in relational data clustering

Danilo Horta*, Ricardo J.G.B. Campello

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

The features describing a data set may often be arranged in meaningful subsets, each of which corresponds to a different aspect of the data. An unsupervised algorithm (SCAD) that performs fuzzy clustering and aspects weighting simultaneously was recently proposed. However, there are several situations where the data set is represented by proximity matrices only (relational data), which renders several clustering approaches, including SCAD, inappropriate. To handle this kind of data, the relational clustering algorithm CARD, based on the SCAD algorithm, has been recently developed. However, CARD may fail and halt given certain conditions. To fix this problem, its steps are modified and then reordered to also reduce the number of parameters required. The improved CARD is assessed over hundreds of real and artificial data sets.

Original languageEnglish
Title of host publicationProceedings of the 2011 11th International Conference on Intelligent Systems Design and Applications, ISDA'11
PublisherIEEE
Publication date2011
Pages522-529
Article number6121709
ISBN (Print)9781457716751
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event2011 11th International Conference on Intelligent Systems Design and Applications, ISDA'11 - Cordoba, Spain
Duration: 22. Nov 201124. Nov 2011

Conference

Conference2011 11th International Conference on Intelligent Systems Design and Applications, ISDA'11
Country/TerritorySpain
CityCordoba
Period22/11/201124/11/2011
SponsorMachine Intelligence Research Labs (MIR Labs), University of Córdoba, Ministry of Science and Innovation of Spain
SeriesInternational Conference on Intelligent Systems Design and Applications, ISDA
ISSN2164-7143

Keywords

  • aspect discrimination
  • feature selection
  • fuzzy clustering
  • relational clustering

Fingerprint

Dive into the research topics of 'Automatic aspect discrimination in relational data clustering'. Together they form a unique fingerprint.

Cite this