Special Issue Article Open Access

Efficient Algorithm for Finding High Utility Itemsets from Large Transactional Databases Using R-Hashing Technique

Abstract

Association rule mining is used to find the frequent item sets in large database. In the data mining field, utility mining emerges as an important topic that to mine the high utility itemsets from databases which refers to finding the itemsets with high profits. The huge number of high utility itemsets makes a challenging problem for the mining performance, due to generating more potential high utility item sets. So it consumes higher process in large database and decreases the mining efficiency. In existing system they have proposed two novel methods such as UPgrowth and UP-growth+ as well as a compact UP Tree data structure, which is used for efficiently discovering high utility itemsets from large transactional databases. In existing system random memory allocation is used to store the candidate that leads to high potential I/O operations. Also this approach is time consuming and requires high memory space. In order to solve this problem in proposed system, we used sorting with R-hashing technique for the memory allocation. Hence the candidate items are stored with their respective memory in UP tree. The experimental result shows that the proposed system is more effective than the existing methods according to the memory space and the number of candidate itemset generation and input and output operations.

D.Sathyavani, Prof. D.Sharmila

To read the full article Download Full Article