Show simple item record  

dc.contributor.authorKranen, Philipp
dc.contributor.authorKremer, Hardy
dc.contributor.authorJensen, Timm
dc.contributor.authorSeidl, Thomas
dc.contributor.authorBifet, Albert
dc.contributor.authorHomes, Geoff
dc.contributor.authorPfahringer, Bernhard
dc.coverage.spatialConference held at Sydney, Australiaen_NZ
dc.identifier.citationKranen, P., Kremer, H., Jense, T., Seidl, T., Bifet, A.,..., Pfahringer, B. (2010). Clustering performance on evolving data streams: Assessing algorithms and evaluation measures within MOA. In Proceedings of 2010 IEEE International Conference on Data Mining Workshops, Sydney, Australia, December 13 (pp. 1400-1403). Washington, DC, USA: IEEE.en_NZ
dc.description.abstractIn today's applications, evolving data streams are ubiquitous. Stream clustering algorithms were introduced to gain useful knowledge from these streams in real-time. The quality of the obtained clusterings, i.e. how good they reflect the data, can be assessed by evaluation measures. A multitude of stream clustering algorithms and evaluation measures for clusterings were introduced in the literature, however, until now there is no general tool for a direct comparison of the different algorithms or the evaluation measures. In our demo, we present a novel experimental framework for both tasks. It offers the means for extensive evaluation and visualization and is an extension of the Massive Online Analysis (MOA) software environment released under the GNU GPL License.en_NZ
dc.publisherIEEE Computer Societyen_NZ
dc.subjectdata streamsen_NZ
dc.subjectevaluation measuresen_NZ
dc.subjectcomputer science
dc.subjectMachine learning
dc.titleClustering performance on evolving data streams: Assessing algorithms and evaluation measures within MOAen_NZ
dc.typeJournal Articleen_NZ
dc.relation.isPartOfICDM2010: The 10th IEEE International Conference on Data Mining Workshopsen_NZ

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record