This paper reviews the application of artificial neural network (ANN) models to time series prediction tasks. We begin by briefly introducing some basic concepts and terms related to time series analysis, and by outlining some of the most popular ANN architectures considered in the literature for time series forecasting purposes: feedforward neural networks, radial basis function networks, recurrent neural networks, and self-organizing maps. We analyze the strengths and weaknesses of these architectures in the context of time series modeling. We then summarize some recent time series ANN modeling applications found in the literature, focusing mainly on the previously outlined architectures. In our opinion, these summarized techniques constitute a representative sample of the research and development efforts made in this field. We aim to provide the general reader with a good perspective on how ANNs have been employed for time series modeling and forecasting tasks. Finally, we comment on possible new research directions in this area.

Purpose – The purpose of this paper is to present a new constrained optimization algorithm based on a particle swarm optimization (PSO) algorithm approach. Design/methodology/approach – This paper introduces a hybrid approach based on a modified ring neighborhood with two new perturbation operators designed to keep diversity. A constraint handling technique based on feasibility and sum of constraints violation is adopted. Also, a special technique to handle equality constraints is proposed. Findings – The paper shows that it is possible to improve PSO and keeping the advantages of its social interaction through a simple idea: perturbing the PSO memory. Research limitations/implications – The proposed algorithm shows a competitive performance against the state-of-the-art constrained optimization algorithms. Practical implications – The proposed algorithm can be used to solve single objective problems with linear or non-linear functions, and subject to both equality and inequality constraints which can be linear and non-linear. In this paper, it is applied to various engineering design problems, and for the solution of state-of-the-art benchmark problems. Originality/value – A new neighborhood structure for PSO algorithm is presented. Two perturbation operators to improve PSO algorithm are proposed. A special technique to handle equality constraints is proposed.

We introduce the PESO+ algorithm (Particle Evolutionary Swarm Optimization Plus) for the solution of single objective constrained optimization problems. A novel feature introduced by PESO+ is an external archive to store and retrieve "tolerant" particles found at past tolerance values. This technique is aimed to preserve particles that otherwise would be lost after the adjustment of the tolerance of equality constraints. Also, two perturbation operators, "c-perturbation" and "m-perturbation" are described. The goal of these operators is to keep diversity and to prevent premature convergence. The constraint handling technique is based on feasibility and summation of constraint violations. All experimental results are reported as required by the organizers of the special session on "Constrained Real Parameter Optimization" at CEC2006.