DEEP LEARNING - BASED OPTIMIZATION OF SMART TRAFFIC SIGNAL SYSTEMS

This paper compares various artificial intelligence techniques applied to intelligent traffic systems for traffic light optimization. The use of Deep Learning algorithms for updating traffic light timings achieves superior results compared to the classical fixed-time approach. The traffic network is conceptualized as a modular component of the urban road infrastructure, facilitating traffic analysis in the context of an integrated management system. A case study analyzes a scenario with multiple connected intersections, with variable input flows estimated based on real data acquired from the Bucharest traffic management system.