Clustering Methodology for Symbolic Data

6Partitioning Techniques

In Chapter , a brief introduction to the principles of techniques to partition a data set into distinct non‐overlapping clusters was presented. In this chapter, how these partitions are obtained for symbolic data is studied.

Partitioning methodology is perhaps the most developed of all clustering techniques, at least for classical data, with many different approaches presented in the literature, starting from the initial and simplest approach based on the coordinate data by using variants of the ‐means methods, or procedures based on dissimilarity/distance measures with the use of the ‐medoids method, or their variations. This includes the more general dynamical partitioning of which the ‐means and ‐medoids methods are but special cases. Not all of these ideas have been extended to symbolic data, and certainly not to all types of symbolic data. Rather than trying to consider each technique where it may, or may not, have been applied to the different respective types of symbolic data, our approach in this chapter is to consider each different type of symbolic data ...