Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

k-Maxoids Clustering

: Bauckhage, C.; Sifa, R.

Volltext (PDF; )

Bergmann, R.:
LWA 2015 Workshops: KDML, FGWM, IR, and FGDB. Proceedings. Online resource : Trier, Germany, October 7-9, 2015
2015 (CEUR Workshop Proceedings 1458)
Conference "Learning, Knowledge, Adaptation" (LWA) <17, 2015, Trier>
Workshop on Knowledge Discovery, Data Mining and Machine Learning (KDML) <2015, Trier>
Workshop "Information Retrieval" (IR) <2015, Trier>
Workshop on Knowledge and Experience Management (FGWM) <2015, Trier>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IAIS ()

We explore the idea of clustering according to extremal rather than to central data points. To this end, we introduce the notion of the maxoid of a data set and present an algorithm for k-maxoids clustering which can be understood as a variant of classical k-means clustering. Exemplary results demonstrate that extremal cluster prototypes are more distinctive and hence more interpretable than central ones.