Traffic congestion poses significant challenges in historic cities striving to balance modern mobility needs and her- itage preservation. This paper proposes a self-adaptive fuzzy logic control system for traffic signals optimized by a recurrent neural network (RNN) for vehicular density prediction. The fuzzy controller dynamically adjusts sig- nal timing based on real-time traffic density data at in- tersections in the colonial cities. The RNN component forecasts traffic density to tune the fuzzy membership functions, enabling adaptive signal control. Simulation experiments demonstrate noticeable reductions in queue length using the proposed neuro-fuzzy method compared to uncontrolled and fuzzy logic only techniques. Improve- ments are positively correlated to street length, although less significant in very short streets. The system demon- strates promising capabilities to reduce congestion and emissions through adaptive optimization in complex ur- ban environments. Keywords: Fuzzy logic control, neural networks, intelli- gent transportation systems, traffic signal timing, conges- tion mitigation