期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：9
DOI：10.15680/IJIRCCE.2015. 0309124
出版社：S&S Publications
摘要：Data stream is used for handling dynamic databases in which data can be arrived continuously, limitlessand its size are very large. This situation has created a problem, i.e. to perform the mining process in these database,the existing data mining algorithms are not suitable. In order to perform mining task in data streams there is a need fordevelopment of new algorithms and techniques. By using this new algorithms and techniques we can able to performvarious data mining tasks, i.e. clustering, classification, frequent pattern mining and association rule mining in datastreams. Association rule mining is used to find the association between the data items which are exist in the databases.Even though, the traditional algorithms are not suitable for data streams, this paper concentrated on how to performassociation rule generation task in data streams using traditional algorithms in order to find the drawbacks as well ascomparing the performance of the traditional algorithms. Frequent Pattern Tree Growth algorithm and APRIORIMap/Reduce algorithms are used for generating association rules in data streams. Performance measures used in thiswork are execution time and number of association rules generated. From the experimental results we come to knowthat the performance of FP-Tree Growth algorithm is more efficient than APRIORI Map/Reduce algorithm.
