Mining stable patterns in multiple correlated databases

Many kinds of patterns (e.g., association rules, negative association rules, sequential patterns, and temporal patterns) have been studied for various applications, but very little work has been reported on multiple correlated databases that are all relevant. This paper proposes an efficient method for mining stable patterns from multiple correlated databases. First, we define the notion of stable items according to two constraint conditions, minsupp and varivalue. We then measure the similarity between stable items based on gray relational analysis, and present a hierarchical gray clustering method for mining stable patterns consisting of stable items. Finally, experiments are conducted on four datasets, and the results of the experiments show that our method is useful and efficient.