DOI: 10.18178/wcse.2019.06.100
An Improved Frequent Pattern Mining Algorithm Based on TB-Tree and Tissue-Like P System
Abstract— The purpose of frequent patterns mining is to find interesting items that appear together in a set
of transactions, as an effective data mining technology, it has been widely used in many fields. Membrane
computing is a new research direction of bio-inspired computing, which utilizes parallel and distributed
computing models to solve problems effectively. In this paper, a new algorithm called ECTP, for mining
frequent patterns, is proposed, which is based on TB-tree and evolution-communication tissue-like P system.
The efficiency of the algorithm is improved by early pruning TB-tree by threshold and the parallelism of
tissue-like P system. The result indicates that the algorithm is accurate and effective, gives some hints to use
parallel operation principle mechanism in membrane computing systems.
Index Terms— Data mining, frequent patterns, tissue-like P system, membrane computing
Linlin Jia, Xiyu Liu, Yuzhen Zhao, Jie Xue
Business school, Shandong Normal University, CHINA
Cite: Linlin Jia, Xiyu Liu, Yuzhen Zhao, Jie Xue, "An Improved Frequent Pattern Mining Algorithm Based on TB-Tree and Tissue-Like P System," Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering, pp. 675-680, Hong Kong, 15-17 June, 2019.