期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2012
卷号：3
期号：4
页码：7-9
语种：English
出版社：Ayushmaan Technologies
摘要：Clustering of data has been of intense need for any organization in the past and various researchers in the field of data mining has been continuously working to find efficient and accurate tools and algorithms for the same. From the proliferation of internet and network applications is pressing the same need more deeply and it is becoming more and more necessary for providing such algorithms by the researchers of data mining. Researchers have been working continuously and finding incremental clustering mechanism to be best suitable for online data. Incremental clustering algorithm clusters data in dynamic form. The database is assumed to be clustered initially, and every new element is added as without need of changing existing clustered database. Basing on the properties of the information, the cluster size will increase incrementally and the information is transferred following an efficient clustering algorithm for mining in a data warehousing environment. Incremental Clustering requires initial clusters to be decided in advance i.e. they must pre exist for processing. If the initial clusters are to be fixed, then there are several ways it can be achieved. This work is proposing a dynamic and novice algorithm for deciding the initial clusters dynamically. In this work an offer is being made to create clusters dynamically after taking a few important characteristics from the user related with database. The characteristics inputted by the user shall be used as parameters to decide the initial clusters and adjusting clusters during processing. Incremental clustering will add the data into various initial clusters and can divide the clusters into more clusters if specific characteristics are matched more nearly.
