MU Digital Repository
Logo

An Efficient Reduced Pattern Count Tree Method for Discovering Most Accurate Set of Frequent itemsets

Geetha, M and D'souza, R J (2008) An Efficient Reduced Pattern Count Tree Method for Discovering Most Accurate Set of Frequent itemsets. International Journal of Computer Science and Network Security (IJCSNS), 8 (8). pp. 121-126.

[img] PDF
RPCT.pdf - Published Version
Restricted to Registered users only

Download (134kB) | Request a copy

Abstract

Discovery of association rules from large volumes of data is an important Data Mining problem. In this paper a novel method for discovering most accurate set of frequent itemsets using partition algorithm is implemented. This method uses the concept of Reduced Pattern Count Tree, Ladder merging and Reduced Minimum Support to discover most accurate set of frequent itemsets in a single scan of database. This algorithm is a modified version of the existing Partition Algorithm, but leads to the significant reduction in time and disk input/ output, and has lower memory requirements as compared to some of the Existing algorithms

Item Type: Article
Uncontrolled Keywords: Frequent itemset, Path, Reduced minimum Support, Reduced Pattern Count Tree
Subjects: Engineering > MIT Manipal > Computer Science and Engineering
Depositing User: MIT Library
Date Deposited: 22 May 2014 09:10
Last Modified: 22 May 2014 09:10
URI: http://eprints.manipal.edu/id/eprint/139562

Actions (login required)

View Item View Item