Thursday 23rd of November 2017
 

An Enhanced Application of Modified PSO for Association Rule Mining


Bharathi.T and P.Krishnakumari

In data mining, association rule learning is a well-liked and well explored technique for finding out interesting relatives in large databases along with variables. It analyzes and present strong rules discovered in databases by means of diverse measures of interestingness. As all know two important parameters, minimal support and confidence, are forever deciding by the decision-maker him/herself or in the course of trial-and-error; and thus, the previous algorithms be deficient in both objectiveness and competence. As a result, the main purpose of proposed work is to recommend an improved algorithm that can provide feasible threshold values for minimal support and confidence. Earliest particle swarm optimization algorithm investigates for the optimum fitness value of each particle and next discovers equivalent support and confidence as minimal threshold values subsequent to the data are distorted into binary values. To improve the feasibility of the work the modified PSO is developed to provide the feasible values. The modified PSO (Particle Swarm Optimization) algorithm has a number of swarm population size, the number of highest generation, and three predetermined parameters will be determined C_w, C_p,C_g. In each generation, the particle€™s position value in all measurements will be reserved or be updated by its pbest value or be updated by the gbest value or restored by generating a new random number.

Keywords: Data Mining, Particle Swarm Optimization, Modified PSO, Minimal Support and Confidence, Association Rule Learning, Swarm intelligence

Download Full-Text


ABOUT THE AUTHORS

Bharathi.T
Bharathi.T completed her Under graduation degree Bachelor of Science B.Sc (Computer Science) in Pioneer college of arts and science affiliated under Bharathiyar University in the duration of 2003-2006 ,She completed her Master of Science(Computer Science) and M.phil In Govt College of Arts and Science affiliated Under Bharathiyar University in the duration 2007-2009 and 2010.Currently she is doing her Ph.D under the Research area of Data Mining. She Successfully submitted one National level conference paper in her academics.

P.Krishnakumari
Dr P.Krishnakumari completed her Under graduation degree Bachelor of Science B.Sc (Computer Technology) in PSG College of Technology, Coimbatore in the duration of 1989-1991 ,She completed her Master of Science(Computer Science) in Avinashilingam University in the year of 1992-1994 and M.phil in Bharathiyar University in the year of 2010. She successfully completed her Ph.D in the field of Data Mining. She had a 12 years of working experience as a Lecturer in Ramakrishna Women’s Arts and Science College, Coimbatore.Currently, she is working as a Director of MCA in RVS Arts and Science College for past 1 year. She successfully submitted 10 National level Journal paper in her career.Her Research area is in the field of Data mining.


IJCSI Published Papers Indexed By:

 

 

 

 
About IJCSI

IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us
FAQs

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »