A cluster validi index based on frequent pattern
a clustering algorithm can produce as many
partitions as desired, one need to assess their quality in order to
select the partition that most represents the structu re in the data.
This is the rationale for the cluster-validity (CV) problem and
indices. This paper proposes a CV index for fuzzy-clustering
algorithm, such as the fuzzy c-means (FCM) or its derivatives.
Given a fuzzy partition, this new index uses global information
and is based on more logical reasoning than geometrical features.
Experimental results on articial and benchmark datasets are
given to demonstrate the performance of the proposed index, as
compared with traditional and recent indices.