An efficient approach for significant time intervals of frequent itemsets
by Somaraju Suvvari; R.B.V. Subramanyam
International Journal of Intelligent Systems Technologies and Applications (IJISTA), Vol. 13, No. 3, 2014

Abstract: Ignoring the time stamps of the transactions may lead to incomplete analysis of patterns and researchers have considered the time stamps of the transactions to get more insight into frequent patterns. It is also noticed that patterns become frequent though their frequency do not spread uniformly over the entire transactional database, rather present in some part of the database might be enough. This observation motivated researchers to design algorithms to perform micro analysis over the database for better understanding of the hidden knowledge. This paper extended the frequent pattern mining framework to extract and associate certain time intervals to each of frequent itemset. We introduced significant time intervals and maximal significant time intervals and proposed an algorithm named as OTIS. Significant time interval (a, b) of a frequent itemset X is extracted based on the support of X in a subset of transactions corresponding to the time interval (a, b). Extraction of significant time intervals of frequent itemsets must be of great interest as they influence business decisions.

Online publication date: Wed, 15-Oct-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Intelligent Systems Technologies and Applications (IJISTA):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com