Research Article
Population Based Search Methods in Mining Association Rules
@INPROCEEDINGS{10.1007/978-3-642-35615-5_39, author={K. Indira and S. Kanmani and P. Prashanth and V. Harish Sivasankar and Konda Teja and R. Jeeva Rajasekar}, title={Population Based Search Methods in Mining Association Rules}, proceedings={Third International conference on advances in communication, network and computing}, proceedings_a={CNC}, year={2012}, month={12}, keywords={Genetic Algorithm Particle Swam optimization Association rules Effectiveness Computational efficiency}, doi={10.1007/978-3-642-35615-5_39} }- K. Indira
S. Kanmani
P. Prashanth
V. Harish Sivasankar
Konda Teja
R. Jeeva Rajasekar
Year: 2012
Population Based Search Methods in Mining Association Rules
CNC
Springer
DOI: 10.1007/978-3-642-35615-5_39
Abstract
Genetic Algorithm (GA) and Particle swarm optimization (PSO) are both population based search methods and move from set of points (population) to another set of points in a single iteration with likely improvement using set of control operators. GA has become popular because of its many versions, ease of implementation, ability to solve difficult problems and so on. PSO is relatively recent heuristic search mechanism inspired by bird flocking or fish schooling. Association Rule (AR) mining is one of the most studied tasks in data mining. The objective of this paper is to compare the effectiveness and computational capability of GA and PSO in mining association rules. Though both are heuristic based search methods, the control parameters involved in GA and PSO differ. The Genetic algorithm parameters are based on reproduction techniques evolved from biology and the control parameters of PSO are based on particle ‘best’ values in each generation. From the experimental study PSO is found to be as effective as GA with marginally better computational efficiency over GA.