An exploratory study of GPS trajectory data using Snap-Drift Neural Network

Research towards an innovative solution to the problem of automated updating of road network
databases is presented. It moves away from existing methods where vendors of road network databases either go
through the time consuming and logistically challenging process of driving along roads to register changes or
use update methods that rely on remote sensing images. For this approach we hypothesize that users of road
network dependent applications (e.g. in-car navigation system or NavSat) could passively record drive
trajectories with the on-board GPS, which would inform digital road network data providers if the user was on a
road that departs from the known roads in the database. Then such drive characteristics would be collected using
the on-board GPS on behalf of the provider. These data would be processed either by an on-board artificial
neural network (ANN) or transferred back to the NavSat provider and input to an ANN along with similar track
data provided by other service users, to decide whether or not to automatically update (add) the “unknown road”
to the road database. As part of this work, in this paper we carry out an exploratory study on the trajectory
information recorded with GPS. Trajectory data collected in London are analysed using a Snap-Drift Neural
Network (SDNN) which categorises them into their strongest natural groupings, by combining clustering with
feature detection in a single ANN. We investigate how the SDNN groups spatio-temporal variations associated
with road traffic conditions. These variations are present in the recorded GPS trajectory data. For our approach
which relies on users to passively record drive trajectory which are then processed as roads or not roads
(Ekpenyong et al., 2007a), it is important to investigate how these variations affects the recorded GPS which
influences the grouping by the SDNN. For our approach a question like – how would SDNN groups GPS
recorded on a road segment in the morning (supposedly heavy traffic) to that recorded in the day (less traffic)?
This issue is investigated in this paper.

Citation:
Ekpenyong, F., Palmer-Brown, D., Brimicombe, A. (2008) ‘An exploratory study of GPS trajectory data using Snap-Drift Neural Network’ Proceedings of Advances in Computing and Technology, (AC&T) The School of Computing and Technology 3rd Annual Conference, University of East London, pp.22-30.