The Normalized-PSO and Its Application in Attribute Weighted Optimal Problem

Traditional PSO(Particle Swarm Optimization) algorithm has the problems of particle cross-border and premature convergence while solving the normalized constrained optimization problem. Our paper uses the attractor and spatial zoom method, and presented the normalized PSO algorithm. Secondly, each attribute is treated equally in the traditional classification algorithm, without considering the differences in attribute measure and contribution, which cause the problem of low classification accuracy. Our paper introduce the use of the normalized PSO algorithm to solve the optimal attribute normalized weighted distance. For example, in KNN classifier, leave-one-out experimental results with multiple UCI data sets show that the classification accuracy using normalization PSO algorithm to calculate normalized weighted distance is higher than using PSO algorithm and traditional none-attribute weighted classifiers.

I. Introduction

Evolutionary algorithms due to its solving process is not affected by the mathematical properties of the objective function, and also to the larger probability converge to global optimal solution, so they are widely used in solving unconstrained optimization problem [1]~[4]. Generally, evolutionary algorithm including: differential evolution, particle swarm optimization algorithm, ant colony algorithm, etc. Among them, particle swarm optimization algorithm for fast convergence rate, simple and widely used. PSO algorithm is inspired in colony foraging behavior such as birds and fish, proposed by Kennedy [5] and Eberhart in 1995 of a global intelligent optimization algorithm. In PSO algorithm, it regard the position of the possible solutions to solve the problem as the space of habitat of birds movement model, then through the information interaction between the individual and gradually increase the possible of finding a better solution in the solving process, and all particles in the group gathered continuously toward the position of the possible solutions. Because the algorithm concept concise, easy implementation, fast convergence rate, less parameter Settings, is a highly efficient search algorithm, is widely used in engineering applications [6]~[8].