These measures are usually tied to the type of criterion being considered in assessing the quality of a clustering method.

The granularity issue has been tackled by proposing clustering methods that automatically group together similar senses of the same word.

There are several types of clustering methods:

Further details, including hard clustering methods, are found in [5].

We first cluster the 1,476 genes using the model-based clustering method described previously using the original data of the log-ratios.

As a comparison, we also applied the hierarchical clustering method to cluster these genes.

Being a clustering method, their effectiveness is higher for low dimensional problems and become less effective for problems having a few hundred variables.

This can be achieved by a simple agglomerative clustering method.

This is mostly achieved by unsupervised hierarchical clustering methods.

Most conceptual clustering methods are capable of generating hierarchical category structures; see Categorization for more information on hierarchy.