Hide/Show Apps

An index structure for fuzzy databases

1996-09-11
Yazıcı, Adnan
Cibiceli, D
Fuzzy querying involves more complex processing than ordinary querying does. In addition, a larger number of tuples will possibly be selected by fuzzy conditions compared to the crisp ones. The current index structures are inefficient in representing and dealing with uncertain and fuzzy data. In this paper we extend one of the multi-dimensional data structures, namely Multi Lever Grid File (Whang and Krishnamurty, 1991) for an efficient access to both crisp and fuzzy data. In order to take advantage of the indexing data structure proposed here, we first partition uncertain data in a way that accessing such data in a database is reasonably efficient. Therefore, we also focus on the issue of preparation of uncertain data before building the access structure. Then we compare the one proposed here with sequential access along with experimental results.