M. Monica Bhavani , K. Uma Maheswari
Geographic information from the global positioning system (GPS) logs of taxi cabs are useful in the novel applications like Smart Maps needed for a city traffic. The historical path logs of the GPS trajectories are mined to provide the landmark graph. Based on the landmark graph and the routing algorithm that uses the variance-entropy based clustering techniques to build and evaluate the system to find the routes in urban areas. Using this system, the road is segmented based on the real world GPS trajectories and a route is evaluated based on the developed landmark graph. This model is used to predict the traffic conditions of the future time. The proposed system is to provide the travelling time, distance and the available number of trajectories between every source and destination in order of predicting an optimised route. On average, 50% of our routes are at least 20% faster than the competing approaches.