On the selection of m for Fuzzy c-Means
2015 (English)In: Proceedings of the 2015 Conference of the International Fuzzy Systems Association and the European Society for Fuzzy Logic and Technology / [ed] José M. Alonso, Humberto Bustince & Marek Reformat, Paris: Atlantis Press , 2015, 1571-1577 p.Conference paper (Refereed)
Fuzzy c-means is a well known fuzzy clustering algorithm. It is an unsupervised clustering algorithmthat permits us to build a fuzzy partition from data. The algorithm depends on a parameter m whichcorresponds to the degree of fuzziness of the solution. Large values of m will blur the classes andall elements tend to belong to all clusters. The solutionsof the optimization problem depend on theparameter m. That is, different selections of m willtypically lead to different partitions. In this paper we study and compare the effect ofthe selection of m obtained from the fuzzy c-means.
Place, publisher, year, edition, pages
Paris: Atlantis Press , 2015. 1571-1577 p.
, Advances in Intelligent Systems Research, ISSN 1951-6851 ; 89
IdentifiersURN: urn:nbn:se:his:diva-11632DOI: 10.2991/ifsa-eusflat-15.2015.224ISI: 000358581100223ISBN: 978-94-62520-77-6OAI: oai:DiVA.org:his-11632DiVA: diva2:865640
16th World Congress of the International Fuzzy Systems Association (IFSA) / 9th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT), Gijon, Spain, June 30-July 3, 2015
Conference general chair: Luis Magdalena Layos2015-10-282015-10-282016-05-30Bibliographically approved