Title :
Validity measures for the fuzzy cluster analysis of orientations
Author :
Hammah, Reginald E. ; Curran, John H.
Author_Institution :
Rocscience Inc., Toronto, Ont., Canada
fDate :
12/1/2000 12:00:00 AM
Abstract :
Fuzzy K-means clustering can be applied to the automatic identification of sets in discontinuity data after suitable adaptation of the algorithm. To establish the number of clusters in a data set, modified versions of the validity measures of Gath and Geva (1989), Xie-Beni (1991) and Fukuyama-Sugeno are presented in this paper
Keywords :
eigenvalues and eigenfunctions; fuzzy set theory; pattern classification; cluster validity measures; eigenvalues; fuzzy cluster analysis; fuzzy set theory; identification; orientations; Algorithm design and analysis; Clustering algorithms; Data analysis; Density measurement; Euclidean distance; Fuzzy sets; Mechanical variables measurement; Partitioning algorithms; Performance analysis; Prototypes;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
