Abstract :
Traveling is a part of every person’s day-today life. With the massive and complicated road network
of a modern city or country, finding a good route to travel
from one place to another is not a simple task. The
knowledge of the actual current state of the road traffic and
its short-term and dynamic path evolution for the entire
road network is a basic component of ATIS (Advanced
Traveler Information Systems) and ATMS Advanced
Traffic Management System) applications. In this view the
use of real-time Taxi Data (TD), based on traces of GPS
positions to gather accurate travel times/speeds in a road
network and to improve short-term predictions of travel
conditions.
GPS-equipped taxis can be regarded as traffic flows on
road surfaces, and taxi drivers are usually experienced in
finding the fastest (quickest) route to a destination based on
their knowledge. We mine smart driving directions from
the historical GPS trajectories of a large number of taxis,
and provide a user with the practically fastest route to a
given destination at a given departure time. In our approach,
we propose a time-dependent landmark graph, where a
node (landmark) is a road segment frequently traversed by
taxis, to model the intelligence of taxi drivers and the
properties of dynamic road networks. The essential
components that will be discussed are a Web-servicesbased data collection approach then, a Variance-EntropyBased Clustering approach is devised to estimate the
distribution of travel time between two landmarks in
different time slots. Based on this graph, we design a twostage routing algorithm to compute the practically fastest
route. In our existing system static (Dynamic)-path and not
update the rout.
Keyword :
Data mining, Spatial databases, Driving directions, time-dependent fast route, taxi trajectories, TDrive, landmark graph