Mining Frequent Itemsets over Vertical Probabilistic Dataset Using FuzzyUeclat Algorithm

Data mining is the technique of extracting relevant information from large heterogeneous data sources and present in a meaningful and systematic way for users. Nowadays, data mining has become a trend and all computer-related industries are engaged with data mining. Currently, many data mining algorithms focused on computing the frequent pattern from certain and uncertain databases. In this paper, a new algorithm named FuzzyUeclat is being proposed which uses Fuzzy operators to extract frequent items from the vertical probabilistic dataset. Previously, the frequent items were computed on the basis of expected minimum support derived from the existential probability associated with items. Therefore, as the size of the database increases, the value of expected support is decreased at each level of iterations and subsequently, it approaches zero. To avoid the loss of frequent itemset, the expected minimum support is being replaced with Fuzzy min and Fuzzy max operator to compute the support for an itemset. The experimental result shows that the algorithm FuzzyUeclat increases the frequent patterns and improves the performance for the large uncertain databases.