Temporal fuzzy association rules mining based on fuzzy information granulation

Abstract

In this paper, we developed a sound conceptual framework for temporal fuzzy association rules mining based on fuzzy information granulation. First, the definition of the support rate of traditional fuzzy association rules is extended to the temporal data, including the fuzzy support rate of both continuous and discontinues temporal fuzzy item set and their association rules. It is found that the computation of support rate under our definition is a simply dynamic programming problem with very low complexity. Then an algorithm based on Apriori is demonstrated. At last, experiments were carried out to show the good performance of our new algorithm in mining continuous rules and discontinuous rules by our definition.