Abstract Views :183 |
PDF Views:3
Authors
Affiliations
1 Department of Computer Science and Engineering, Velammal College of Engineering and Technology, Madurai-625009, Tamilnadu, IN
Source
Data Mining and Knowledge Engineering, Vol 6, No 2 (2014), Pagination:
Abstract
In Efficient driving direction system, the GPS-equipped vehicle are used as mobile sensors thereby probing the traffic rhythm of a city. It helps the drivers in choosing driving directions. The smart driving directions can mine from the historical GPS trajectories. A time-dependent landmark graph is framed with the view of modeling the dynamic traffic pattern and also the intelligence of experienced drivers. Hence it helps assist the user by providing the practically fastest route to a given destination at a given time of departure. The Variance Entropy-Based Clustering method is employed to estimate the distribution of travel time between two landmarks in different time slots. Taking this graph as a basis, a two-stage routing algorithm is used to compute the practically fastest and customized route for end users. Necessarily, the time taken by a driver to traverse a route depends on the following aspects:1) The physical feature of a route such as distance, capacity (lanes), and the number of traffic lights, number of direction turns; 2) The time-dependent traffic flow along the route; 3) The driving behavior of a user.
Keywords
Driving Directions, Time-Dependent Fast Route, Taxi Trajectories, Landmark Graph.
