The aim of the project is to develop traffic management algorithms at microscopic and mesoscopic levels using big data, sensor integration and machine learning algorithms to dynamically optimize urban traffic flow along the corridor. At the microscopic level, real-time traffic data (volume, speed, vehicle length, headway, trajectory) will be collected at intersections and the signal duration of intersections will be optimized. This data will be transmitted to the traffic management center and re-optimized at the mesoscopic level, integrated with corridor-wide signal duration optimizations. The ultimate goal of the project is to reduce the number of stops, delay time, travel time, fuel consumption and carbon emissions on the cities' main roads.