Login New user?  
Applied Mathematics & Information Sciences Letters
An International Journal
               
 
 
 
 
 
 
 
 
 
 
 
 

Content
 

Volumes > Vol. 04 > No. 2

 
   

Clustering Uncertain Graph Data Stream

PP: 85-96
doi:10.18576/amisl/040206
Author(s)
Zahra Varaminy Bahnemiry, Mir Mohsen Pedram, Mitra Mirzarezaee,
Abstract
Today, according to the increasing spread of information which people deal with, taking advantage of methods such as data mining to extract hidden knowledge from data is inevitable. Due to the extremely high volume of data in many applications and higher importance of new data, storage of these data is not effective in cost, so clustering these data is more important because of the data that are processed are always changing dynamically. Another problem in data mining is the issue of clustering of graph data stream. According to a number of existing algorithms for graph data stream clustering, choosing an appropriate algorithm has been challenged. The concept of graph micro cluster has been used in clustering of graph data stream which its challenge is time and space complexity. On the other hand, the uncertainty in edge graph stream should be taken into consideration to ensure reliable results that have not been investigated in studies so far. In this paper, a novel algorithm, for clustering of graph data stream considering uncertainty is investigated in a dynamic environment. Generally, the main innovation of this paper is to provide an approach for clustering uncertain graph data stream possessing a concept drift and dynamic. The results of the experiments conducted in this paper indicate the suitability of the proposed approach to this problem. Its time and space complexity is also reasonable.

  Home   About us   News   Journals   Conferences Contact us Copyright naturalspublishing.com. All Rights Reserved