×

Reduction of discriminant rules based on frequent item set calculation. (English) Zbl 1001.68037

Jain, Lakhmi C. (ed.) et al., New learning paradigms in soft computing. Heidelberg: Physica-Verlag. Stud. Fuzziness Soft Comput. 84, 419-438 (2002).
Summary: Reduction of the number of attributes to calculate rules in large databases is of great interest in data mining. In this paper, we propose a method for reducing the number of attributes in rules using frequent item sets calculation. The method is based in a basic step model. In our approach algorithms are divided in atomic operations that have been called basic steps so that it is easier to optimize the execution of any algorithm. We also present the implementation of this approach in Damisys what demonstrates that our approach is implementable and effective dealing with large datasets.
For the entire collection see [Zbl 0978.00024].

MSC:

68P15 Database theory