In this paper a new cluster validity index is introduced, which assess
es the average compactness and separation of fuzzy partitions generate
d by the fuzzy c-means algorithm. To compare the performance of this n
ew index with a number of known validation indices, the fuzzy partitio
ning of two data sets was carried aut. Our validation performed favora
bly in all studies, even in those where other validity indices failed
to indicate the true number of clusters within each data set. (C) 1998
Elsevier Science B.V. All rights reserved.