期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2017
卷号：6
期号：12
页码：1886-1889
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Data Mining is the extraction of hidden information from large databases called knowledge discovery in databases (KDD). Association Rule is used to detect the frequent item sets and also useful for discovering relationship among items from large databases. As the hardware’s capacity is constant, the number of candidate itemsets is increased than the capacity of the hardware. It will create performance blockage. The hash-based and pipelined (HAPPI) architecture is to compare itemsets with the large databases and to decrease the number of candidate itemsets. HAPPI architecture includes 3methods such as Systolic array, Trimming filter and Hash table filter. Systolic array method is used to compare candidate itemsets with databases and then minimum support count value can be calculated. Trimming filter is used to decrease the items from each transaction. Hash table filter is used to decrease the itemset by finding or detecting duplicate records in the large databases. In hash table filter, MD5 algorithm is to be implemented. MD5 algorithm is mainly used to decrease the duplicate databases in the hardware. MD5 also proposed for other applications, where a large sized file must be compressed in a secure manner before being encrypted with a secret key under a public-key cryptosystem.
