Flash News
Welcome to IARC

Publisher Login

Latest News
Welcome to IARC- JCR Report

Submit your Journal to get IARC-JCRR Indexing and Impact Factor
 

Impact Factor calculated by IARC on the basis of Journal Citation Reference (JCR) Report.

 

Contact: iarcdpi@gmail.com

 

A NOVEL APPROACH FOR FREQUENT DATA PARTITIONING USING PARALLEL MINING ITEMSETS AND HADOOP
C.Yosepu, K Ganapathi Babu, D Harith Reddy

Published in: International Journal of Current Engineering And Scientific Research ( IJCESR)
Volume- 5, Issue-1, pp.92-96, Jan 2018
DPI :-> 16.10046.IJCESR.2018.V5I1.9296.2303



Abstract
Parallel traditional algorithms are used for mining frequent itemsets. Traditional parallel mining algorithms partition the data equal among a group of computing nodes. Existing parallel Frequent Itemset Mining algorithms have serious performance problems. Data partitioning strategy is used to resolve the problem Given a huge dataset, data partitioning strategies in the existing solutions endure high communication and mining overhead provoked by redundant transactions transmitted among computing nodes. We address this problem by Hadoop The core of Apache Hadoop contains a storage part, known as Hadoop Distributed File System (HDFS), and a processing part called as Map Reduce. Hadoop divides files into large chunks. It dispense them across computing nodes in a cluster. By using this approach the performance of existing parallel frequent-pattern increases. This paper shows the different parallel mining algorithms for frequent itemsets mining. We summarize the different algorithms that were developed for the frequent itemsets mining, like candidate key generation algorithm, such as Apriori algorithm and without candidate key generation algorithm, such as FP-growth algorithm. These algorithms does’t have mechanisms like load balancing, data distribution I/O overhead, and fault tolerance.The efficient method is the FiDoop using ultrametric tree (FIUT) and Mapreduce programming model. FIUT scans the database two times. FIUT has four advantages. First: It reduces the I/O overhead as it scans the database two times. Second: only frequent item sets in each transaction are inserted as computing nodes for compressed storage. Third: FIU is enhanced method to partition database, which extensively reduces the search space. Fourth: frequent itemsets are created by examining only the leaves of tree rather than traversing complete tree, which decrease the computing time.

Key-Words / Index Term
Data Mining, Recommender Systems, Social Network

How to cite this article
C.Yosepu, K Ganapathi Babu, D Harith Reddy , “A NOVEL APPROACH FOR FREQUENT DATA PARTITIONING USING PARALLEL MINING ITEMSETS AND HADOOP”, International Journal of Current Engineering And Scientific Research ( IJCESR), 5, Issue-1, pp.92-96, Jan 2018. DPI:16.10046.IJCESR.V5.I1.2303