A new method for mining colossal patterns
Thanh-Long Nguyen, Bay Vo, Loan T. T. Nguyen · 2016
Sohrabi and Barforoush proposed the BVBUC (Bitwise vertical bottom up colossal) algorithm for mining colossal patterns based on a bottom up scheme. It, however, spends more time to check subsets and supersets, because it generates a lot of candidates and consumes more memory usage to store these. In this paper, we propose a new method for mining colossal patterns. Firstly, the CP (Colossal Pattern)-tree is designed. Next, we develop two theorems to fast compute patterns of nodes and prune nodes. Based on the CP-tree and these theorems, an algorithm (named CP-Miner) is proposed to solve the problem of mining colossal patterns. Experimental results show that CP-Miner is more efficient than BVBUC in both the mining time and search space.