期刊名称:International Journal of Grid and Distributed Computing
印刷版ISSN:2005-4262
出版年度:2016
卷号:9
期号:11
页码:285-298
出版社:SERSC
摘要:In currentyears,data streams have been gradually turn into mostimportant research area in the field of computer science.Data streams aredefined as fast,limitless, unbounded, river flow, continuous, stop less, massive, tremendousunremitting, immediate, streamflow,arrival of ordered and unordered data. Data streamsare dividedintotwo types,they are onlineandofflinestreams. Online data streams are mainly used for real world applicationslike face book, twitter, network traffic monitoring, intrusion detection and credit cardprocesses. Offline data streamsaremainly usedformanipulatingthe informationwhich isbased onweb log streams. In data streams, data size is extremely huge and potentially infinite and itis not possible to lay upall the data, so it leads to a mining challenge where shortageof limitations has occur in hardware and software. Data mining techniques such as clustering,load shedding,classificationandfrequent pattern mining are to be applied in data streams to get useful knowledge. But, the existing algorithms are not suitable for performing the data mining process in data streams; hence there is a need for new techniques and algorithms.The main objective of this research work is to perform the clustering process in data streams and detecting the outliers in data streams.New hybrid approach is proposed which combines the hierarchical clustering algorithm and partitioningclustering algorithm. In hierarchical clustering, CURE algorithm is used and enhanced (E-CURE) and in partitioning clustering, CLARANS algorithm is used and enhanced (E-CLARANS). In this research work, the two algorithms E-CURE and E-CLARANS are combined (Hybrid) forperforming a clustering process andfinding the outliers in data streams.The performance of this hybrid clustering algorithm is compared with the existinghybrid clustering algorithmsnamely BIRCHwith CLARANS and CUREwith CLARANS.Theperformance factors used in this analysis are clustering accuracy andoutlier detectionaccuracy. By analyzing the experimental results, it is observed thatthe proposedhybrid clustering approach E-CURE with E-CLARANSperformance is more accurate than the existinghybrid clustering algorithms.