Marius TEME1, Catalin DIMON2
Abstract. 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.
Keywords: Deep Learning, optimization, traffic light systems, variable cycle, number of cars, congestion
DOI 10.56082/annalsarsciinfo.2025.1.5
1 PhD, Eng., Faculty of Automatic Control and Computers, National University of Science and Technology Politehnica Bucharest, Splaiul Independentei nr. 313, Sector 6, Bucharest, 060042, Romania, Academy of Romanian Scientists, e-mail: marius.teme@upb.ro
2 Prof., Eng., Faculty of Automatic Control and Computers, National University of Science and Technology Politehnica Bucharest, Splaiul Independentei nr. 313, Sector 6, Bucharest, 060042, Romania, Academy of Romanian Scientists, e-mail: catalin.dimon@upb.ro.
PUBLISHED in Annals of the Academy of Romanian Scientists Series on Science and Technology of Information, Volume 18, No1
ISSN PRINT2066 – 2742 ISSN ONLINE 2066-8562 
Description | Editorial Board | Instructions for authors | Template 
| Archive