Optimización de la Semaforización Inteligente para la movilidad urbana con inteligencia artificial e IOT

Abstract

Urban mobility efficiency is a major problem in modern cities due to the constant increase of vehicular traffic. This study presents an innovative architecture for the optimization of intelligent traffic signalization in urban environments using Artificial Intelligence (AI) and the Internet of Things (IoT). The main objective is to develop a model that improves urban mobility by integrating vehicular flow sensors and pedestrian detection, leveraging the predictive capabilities of Recurrent Neural Networks (RNN). A literature review was conducted to identify the fundamentals and advances in intelligent urban mobility, followed by the design of a scalable, flexible and secure information architecture. The comparative evaluation of the proposed model, using Multi-Criteria Analysis (MCA), showed that the architecture outperforms other approaches in terms of performance, scalability, robustness, and flexibility, concluding on its feasibility for further implementation in environments with increasing urban mobility challenges.