Inter Transactional Association Rule Mining using Boolean Matrix
Journal Title: International Journal of Research in Computer and Communication Technology - Year 2012, Vol 1, Issue 2
Abstract
One of the extensions of the data mining is Temporal data mining, which mines or discovers knowledge and patterns from temporal information which includes time attribute analysis. From the various types of temporal association rule mining, much of the literature focuses on intra transaction association rules, which deal with relations within transactions. Only a few algorithms exist to mine inter transaction association rules, where relations across transactions are analyzed. With the help of inter transactional association rules, one can achieve the benefits to know that the item B follows the item A, but also get an indication on when this is supposed to happen. This paper is presenting preliminary framework to find interesting temporal inter transactional associated patterns with the help of modification in data preparation step and with the help of Boolean matrix to process the data. During the data preparation step, the transaction data are converted to Mega transactions. We apply this step after the generation of 1-frequent items, so that it helps to reduce the number of items in the Mega transactions. And then, completing remaining part of frequent item analysis to discover the temporal relationships from data. As the Boolean matrix is generated from the Mega transactions no more dataset scanning is required and thus minimizes the overall execution time.
Authors and Affiliations
Dipti Rana, N. J. Mistry, M. M. Raghuwanshi
Keywords
Related Articles
- EP ID EP27435
- DOI -
- Views 453
- Downloads 8
A Distributed Algorithm for identifying failures in WSN
A wireless sensor network is a technology for monitoring physical or environmental conditions such as temperature, pressure, sound etc. A WSN can get separated into multiple connected sensors. But some nodes may fail...
To Enable Base Station To Obtain The ‘True’ Estimate Of The Aggregate In The Presence Of The Attack
The sensor nodes appearance a multi-hop network as the base station (BS) proceeds as the central point of control. Wireless sensor networks used in different kinds of applications like Forest monitoring, weather fore...
Enhancement Of Power Quality Under Different Fault Condictions And Harmonic Elimination By Using D-Statcom
this paper mainly focuses on power quality with D-STATCOM Due to the non-standard voltage, frequency, and current at distribution side. In this paper the role of DSTATCOM (Distribution Static Compensator) are located...
Para-Scheduling Algorithm for Architectural Framework of Virtual Computing Lab
Our main concern in private cloud computing is to provide sufficient computing resources on demand, however in current architectures like eucalyptus, cluster controller is the sole provider of virtual machines to the...
Clustering For Non sentence Data Sets Using HFRECCA (Hierarchical Fuzzy Relational Eigenvector Centrality based Clustering Algorithm)
Clustering is the process of grouping or aggregating of data items. Sentence clustering mainly used in variety of applications such as classify and categorization of documents, automatic summary generation, organizin...