2005 | OriginalPaper | Buchkapitel
Optimal Fuzzy Modeling Based on Minimum Cluster Volume
verfasst von : Can Yang, Jun Meng
Erschienen in: Advanced Data Mining and Applications
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 proposes a new fuzzy modeling method, which involves the Minimum Cluster Volume clustering algorithm. The cluster centers founded are naturally considered to be the centers of Gaussian membership functions. Covariance matrix obtained from the result of cluster method is made use to estimate the parameters
σ
for Gaussian membership functions. A direct result of this method are compared in our simulations with published methods, which indicate that our method is powerful so that it solves the multi-dimension problems more accurately even with less complexity of our fuzzy model structure.