Ardalan Vahidi Clemson University This talk presents an in-vehicle decision support system for improving the energy efficiency of a connected car in arterial roads and evaluates its impact on mixed traffic via micro-simulations. In one experimental case study, we show that by communicating the state of traffic signals to a connected car the idling times at red lights are reduced and energy efficiency is increased. Obtaining the timing of traffic lights is one of the main challenges of this work. In this case study we successfully “crowed-source” traffic signal timings from statistical patterns in motion of sparse vehicular probe data in the city of San Francisco. We show other use cases of such data for traffic control decision support.