Comprehensive Study of Weighted Sequential Pattern Mining
Niti Desai1, Amit Ganatra2
1Niti Desai, Deprtment of Computer Engg, Uka Tarsadia University, Bardoli, Surat, Gujarat, India.
2Amit Ganatra, U and P U Patel Department of Computer Engineering, Charotar University of Science and Technology, Changa, Anand, Gujarat, India.
Manuscript received on April 05, 2013. | Revised Manuscript received on April 27, 2013. | Manuscript published on May 05, 2013. | PP: 185-188 | Volume-3, Issue-2, May 2013. | Retrieval Number: B1491053213/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Extensive growth of data gives the motivation to find meaningful patterns among the huge data. Sequential pattern provides us interesting relationships between different items in sequential database. In the real world, there are several applications in which specific sequences are more important than other sequences. Traditional Sequential pattern approaches are suffering from two disadvantages: Firstly, all the items and sequences are treated uniformly. Second, conventional algorithms are generating large number of patterns for lower support. In addition, the unimportant patterns with low weights can be detected. This paper addresses problem of traditional framework and various framework of weighted sequential pattern. Paper also discuses how algorithm mines sequential pattern which reduces the search space and new pruning technique prune the unimportant pattern and pick only those patterns which leads to important and emerging pattern. Later section of paper discuses results of simulation study and how researcher can lead current research.
Keywords: Weighted Sequential Pattern Mining, Weighted Association Mining Framework, Weighted sequential pattern Mining Framework.