Abstract
|
Article Information:
Sequential Pattern Mining by Multi- Threading Techniques
Reza Noorian Talouki and Mehdi Sobhkhiz Talouki
Corresponding Author: Hamid Alinejad-Rokny
Submitted: January 11, 2012
Accepted: March 15, 2012
Published: October 01, 2012 |
Abstract:
|
Discovery of Sequential pattern mining is an important data mining mission with wide applications.
One of the most important types of sequential patterns is closed sequential pattern, which holds all the
information of the perfect patterns set but is much more compact than it. There is no model that used multithreading
techniques for parallel mining of closed sequential patterns. In this paper an algorithm called
MTMCSP (multi-thread mining of closed sequential patterns) is recommended to conduct parallel mining of
closed sequential patterns on a multi-processor system as a multi-threading technique. MTMCSP divides the
works among the tasks by using the divide-and-conquer property. The proposed algorithm has used dynamic
scheduling to avoid task idling, moreover we have employed a technique, called random selecting. The
experimental results show that MTMCSP attains good parallelization efficiencies on various input datasets.
Key words: Multi-threading , sequential patterns, thread scheduling, , , ,
|
Abstract
|
PDF
|
HTML |
|
Cite this Reference:
Reza Noorian Talouki and Mehdi Sobhkhiz Talouki, . Sequential Pattern Mining by Multi- Threading Techniques. Research Journal of Applied Sciences, Engineering and Technology, (19): 3552-3557.
|
|
|
|
![](http://www.maxwellsci.com/images/RJASET-maxw.jpg) |
ISSN (Online): 2040-7467
ISSN (Print): 2040-7459 |
![Submit Manuscript](../images/sub.jpg) |
Information |
|
|
|
Sales & Services |
|
|
|