http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Frequent Itemset Mining Based-on Apriori Algorithm
Le Thi Thanh Nhan 경희대학교 2010 국내석사
The frequent itemset mining problem first has been formulated in 1993 as the computational relevant step in association rule mining. Given a sequence of itemsets, we have to find itemsets that are contained as a subset in more than a given number of elements of the sequence. A huge amount of papers have been published about algorithms to solve this task. Apriori is the first proposed algorithm to find frequent itemsets in a database. Most of its improvements used prefix tree to compress the database. In my research, I introduce a new Apriori-based algorithm which uses bit streams to represent the database. For experiments I compare our method with some Apriori-based state of the arts. Experiments involving typical real and synthetic datasets reveal that my work outperforms most of other Apriori-based algorithms.