Abstract:The paper promotes the implementation of a neural network approach to improve one of the most transcendent traffic conditions: the mobility of the cars in any particular junction. Neural networks have proven to be an effective paradigm of modern computing, providing extensive benefits in a wide range of applications. In this sense, the paper uses a BPNN (backpropagation neural network) model. The three input nodes are related to: n1: the amount of cars in the road; n2: the green light interval; and n3: the distance (taking into account the quantity of cars) between the first car in the intersection and the last car in the longest line in front of it. In particular, the paper promotes that each traffic light signal will be capable of offering a new green light interval according to the requirement and constrains of the vitality, ensuring a vehicular mobility level greater than 65%. To assess this idea, the paper presents two experiments confronting the real world data versus experimental results. For example, in the first experiment, the BPNN improves the performance of the real data about vehicular mobility in almost 30%. Finally, some conclusions and future work are presented.