Adaptive neuro-fuzzy inference system for traffic cycle optimization

AbstractAn adaptive neuro-fuzzy approach is employed to optimize the traffic cycle on Al-Rabia signalized intersection in Amman, the capital of Jordan. A structural fuzzy framework is proposed to estimate traffic flow volumes on the intersection using actual traffic counts for four weeks. More than 80% of the data is used to train the model, and the rest is used to test the generalization capability of the model. Results show that the neuro-fuzzy approach is better in estimating traffic volume than the neural networks approach.