An Algorithm of Frequent Patterns Mining Based on Binary Information Granule

To get rid of these traditional frameworks for discovering frequent association patterns, this paper proposes an algorithm of frequent association patterns mining based on binary information granule, which is mainly different from the Apriori framework and the FP-growth framework. The algorithm generate candidate by Boolean complementation to avoid connecting candidate operation of the Apriori framework, and compute support by the intersection of binary information granules to avoid to repeatedly read the database; it also adopts a linear array to avoid using complex data structure similar to the FP-growth framework. Based on these comparisons of experiments, the results indicate that the proposed algorithm is better than the traditional mining frameworks, particularly, the Apriori framework and the FP-growth framework.