Interpretable knowledge discovery from data with DC*

We present DC* (Double Clustering with A*) as an information granulation method specifically suited for deriving interpretable knowledge from data. DC* is based on two main clustering stages: the first is devoted to compressing multi-dimensional data into few prototypes that grab the main relationships among data; the second is aimed at finding a proper fuzzy granulation of each input feature so that the relations among data can be linguistically described in terms of fuzzy classification rules. We applied DC* as a stage in a knowledge discovery process, aimed at finding interpretable diagnostic rules for sleep-related breathing disorders.