Traffic congestion in urban areas significantly affects travel time, fuel consumption, and affects environmental quality. In this research work, the optimization of traffic signal timing in an urban area has been performed considering PCU, lane width, and some other critical parameters. The conventional techniques used to control traffic signals are either fixed-time or actuated control and thus not very efficient in response to changing dynamics in urban traffic flow conditions. In our proposed system, we adapt the intelligent machine learning and hybrid optimization algorithm for the development of the adaptive signal control system. Procedures include real-time data collection, calculation of PCU, measurement of lane width, and analysis of traffic flow. The settings of the signals are determined by using an optimization hybrid algorithm. This system updates the signal settings continuously in regard to real-time traffic conditions through a feedback loop for continuous learning and adaptation. It ensures high efficiency in traffic flow, with about a 20% improvement in the proposed system, and a reduction of 15% on average vehicle delay, 10% fuel consumption, and 10% emissions compared to traditional methods in the middle-sized urban areas. While this approach guarantees significant improvements, it recognizes a number of challenges regarding technical difficulties of real-time integration data and extensive calibration over different urban environments. The presented work provides a strong pattern of mitigation strategies that can be adopted to improve the efficiency of the flow of traffic in urban areas.