Heuristic algorithm for interpretation of multi-valued attributes in similarity-based fuzzy relational databases

In this work, we are presenting implementation details and extended scalability tests of the heuristic algorithm, which we had used in the past [1,2] to discover knowledge from multi-valued data entries stored in similarity-based fuzzy relational databases. The multi-valued symbolic descriptors, characterizing individual attributes of database records, are commonly used in similarity-based fuzzy databases to reflect uncertainty about the recorded observation. In this paper, we present an algorithm, which we developed to precisely interpret such non-atomic values and to transfer the fuzzy database tuples to the forms acceptable for many regular (i.e. atomic values based) data mining algorithms.