Map matching for error prone GPS data on a sparse road network and predicting travel time of a route

Optimal ambulance route detection in an urban area is a challenging problem especially in the presence of difficulties such as sparse road network, error-prone GPS data and irregular traffic conditions. We have worked on solutions robust to these challenges and for the first time ever in the context of Dhaka, Bangladesh. This paper presents our newly designed map-matching algorithms as well as an intelligent route prediction scheme. We have implemented our algorithms on real traffic data and discuss the results here.