Particle Swarm Classifiers

A method is described for finding the decision functions for classifying patterns in the feature spaces, using particle swarm optimization (PSO). The results show that the performance of this new swarm intelligence classifier is comparable to, or better than knearest neighbour (k-NN) and multi layer perceptron (MLP) classifiers, where the performance of these two classifiers depends heavily on the value of k and the architecture respectively. Iris data as a benchmark and automatic radar target recognition as a practical problem are two examples for classification.

کلیدواژه ها:

Particle swarm optimization ، Pattern recognition ، Multi layer perceptron ، k-nearest - neighbour