Anzeige
Erschienen in:
2010 | OriginalPaper | Buchkapitel
DK-BKM: Decremental K Belief K-Modes Method
verfasst von : Sarra Ben Hariz, Zied Elouedi
Erschienen in: Scalable Uncertainty Management
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This paper deals with the dynamic clustering under uncertainty by developing a decremental K Belief K-modes method (DK-BKM). Our clustering DK-BKM method tackles the problem of decreasing the number of clusters in an uncertain context using the Transferable Belief Model (TBM).
The proposed approach generalizes belief K-modes method (BKM) to a dynamic environment. Thus, this so-called DK-BKM method provides a new clustering technique handling uncertain categorical attribute’s values of dataset objects where dynamic clusters’ number is considered. Using the dissimilarity measure concept makes us to update the partition without performing complete reclustering. Experimental results of this dynamic approach show good performance on well-known benchmark datasets.