Improved frequent item-sets mining in pharmacovigilance

Abstract

Mining frequent item-sets is an important concept that deals with fundamental and initial task of data mining. Apriori is the most popular and frequently used algorithm for finding frequent item-sets which is preferred over other algorithms like FP-growth due to its simplicity. For improving the time efficiency of Apriori algorithms, Jiemin Zheng introduced Bit-Apriori algorithm with the enhancement of support count and special equal support pruning with respect to Apriori algorithm. In this paper, a novel Bit-Apriori algorithm, that deletes infrequent items during trie2 and subsequent tries are proposed which can be used in pharmacovigilance to identify the adverse event.