Traffic Signal Prediction Using Elman Neural Network and Particle Swarm Optimization

Prediction of traffic is very crucial for its management. Because of human involvement in the generation of this phenomenon, traffic signal is normally accompanied by noise and high levels of non-stationarity. Therefore, traffic signal prediction as one of the important subjects of study has attracted researchers' interests. In this study, a combinatorial approach is proposed for traffic signal prediction, based on Neural Networks and Particle Swarm Optimization algorithm. Elman Neural Network is chosen from amongst many types of Neural Networks due to its feedbacked structure. To this purpose, Particle Swarm optimization algorithm is utilized for adequate training of the Neural Network, instead of common gradient descent based methods. In this work, wavelet transform is employed as a part of the preprocessing stage, for the elimination of transient phenomena as well as for more efficient training of the Neural Network. Simulations are carried out to verify performance of the proposed method, and the results demonstrate good performance in comparison to other methods.