Attribute Reduction Method Using Adaptive Genetic Algorithm and Particle Swarm Optimization

Abstract

Attribute reduction is one of the core contents in rough set knowledge discovery, how to find the minimal attribute reduction, proposes an attribute reduction method using adaptive Genetic Algorithm(GA) and Particle Swarm Optimization(PSO). On the basis of the condition attributes for decision attribute support degree, the method reset the fitness function, can dynamically adjust the parameters of the function, thus to ensure the obtained results for minimal reduction, combined with the genetic algorithm of adaptive crossover and mutation operation, to ensure that the particles in the feasible solution can be fully retain and use, the method to strengthen the local search ability at the same time, but also keep the global search ability. Experiments results show that the method has obvious advantages in solving the minimum attribute reduction.