An Improved IFP-growth Algorithm Based on Tissue-Like P Systems with Promoters and Inhibitors

The FP-growth is an effective method of mining frequent itemsets to find association rules. But this algorithm scans the database twice to create a FP-tree. This process reduces the efficiency of the algorithm. An improved method, the TPPIIFP-growth algorithm, is presented and uses two-dimensional vector table and tissue-like P systems with promoters and inhibitors to improve the original algorithm. While reducing the scanning, using the flat maximally parallel reduces the time complexity. And this method can be applied to other similar algorithms.