Finding Pattern in Large Graph Database using Mapreduce (Hadoop)
Author(s):
Mr. M.Rammurthy , Anna university regional center coimbatore; Dr. P.Marikkannu, Annna university regional center,Coimbatore
Keywords:
Frequent subgraph Mining, candidate pattern generation, Graph Data, Iterative Mapreduce, Distributed database
Abstract:
Handling the massive data in a single database is more complex to process and mining. So, Data is stored in Distributed manner and it co-ordinates together by mapreduce framework. In real world prediction plays a vital role. The same way, Here in biological dataset pattern mining is possible through finding relationship between them. Finding relationship and co-relating the words (nodes) is quite simple in graph. So, we used graph structured database. An important node pair is referred as candidate key pair to match the entire frequent subgraph in particular partitioned data. An iterative mapreduce is used to generate global frequent subgraph mining in distributed database.
Other Details:
| Manuscript Id | : | IJSTEV2I10314
|
| Published in | : | Volume : 2, Issue : 10
|
| Publication Date | : | 01/05/2016
|
| Page(s) | : | 1118-1121
|
Download Article
