Application of Particle Swarm Optimization Algorithm to Neural Network Training Process in the Localization of the Mobile Terminal

In this paper we apply Particle Swarm Optimization (PSO) algorithm to the training process of a Multilayer Perceptron (MLP) on the problem of localizing a mobile GSM network terminal inside a building. The localization data includes the information about the average GSM and WiFi signals in each of the given (x,y,floor) coordinates from more than two thousand points inside a five story building. We show that the PSO algorithm could be with success applied as an initial training algorithm for the MLP for both classification and regression problems.