Adaptive Bare Bones Particle Swarm Optimization for Feature Selection

Feature selection is a useful pre-processing technique for solving pattern classification problems. In this paper, we propose a new method of feature selection based on an adaptive bare bones particle swarm optimization. First, we use the logistic equation of chaotic systems to initialize the particle swarm. Then, the adjacent algorithm (KNN) is used as a classifier to evaluate the achievement of the standard data set. The experimental results show that the new algorithm achieves better classification accuracy or uses fewer features than the other compared feature selection methods.