Managing Traffic Incidents - University of Queensland

(Continued from page 25)
Thomas, K and Dia, H (2000a) A Neural Network
Model for Arterial Incident Detection Using Probe
Vehicle and Loop Detector Data, Proceedings of
the 22nd Conference of Australian Institutes of
Transport Research (CAITR 2000), 6-8 December
2000, Australian National University, Canberra
Australia.
This paper describes a research project which
aims to demonstrate the feasibility of using
real-time traffic measurements to develop an
automated arterial incident detection model
using a neural network. The travel time data
needed for model development will be collected
from probe vehicles (public transportation
buses) that transmit travel time data as
they traverse various links of the road network;
and from fixed electronic detection
devices (inductive loop detectors) embedded
in the pavement of the road.
The models proposed in this research will
use the probe vehicle and fixed detector data
to automatically detect any incidents (e.g.
accidents, disabled vehicles, spilled loads etc.)
that reduce the capacity of the road and result
in queues, delays and increased travel times
for travellers. Early detection of such incidents
can help traffic authorities respond
quickly, dispatch emergency services to the
incident site and divert traffic in order to
reduce delays. Unlike previous studies which
relied on simulated probe vehicle and loop
detector data, this project will be based on
real-world data to be collected from Gympie
Road in Brisbane. The models proposed in
this research project will provide road authorities
with quick and reliable incident detection
aimed at reducing congestion, improving air
quality and enhancing the performance of the
road network.
Non-recurrent congestion resulting from
accidents, breakdowns and other incidents
accounts for about 60% of the delays on
freeways. Therefore, the sooner an appropriate
incident response is implemented, the less
impact the incident will have on road user
safety, congestion and the environment.
Various models have been developed for
AID from a variety of theoretical backgrounds
and data sources. However, most of these
models have limitations, namely high false
alarm rates or difficulties with portability and
configuration. Artificial neural networks have
had the most success, with low false alarm
rates and relatively easy configuration.
The use of fractal dimension analysis is
becoming widespread. Experts in fields as
diverse as Medicine, Physics, Seismology,
Economics, Meteorology and Ecology are
using fractal dimension analysis to quantify
various phenomena. Fractal analysis has been
used to model traffic flow, but does not
appear to have been used for incident detection.
Two fractal models were developed and
tested on a data set of 100 incidents which
were collected by VicRoads for the development
of artificial neural network incident
detection models. A similar methodology to
that presented by Dia and Rose was used in
this project so that the results of the fractal
models could be compared with those of the
ARRB/VicRoads and the Artificial Neural
Network Models. !
Copies of papers can be downloaded from
http://www.uq.edu.au/dia/publications.html
26 DECEMBER 2001
Thomas, K and Dia, H (2000b) Incident Detection
by Fractal Dimension Analysis of Loop Detector
Data, Proceedings of the 22nd Conference of
Australian Institutes of Transport Research (CAITR
2000), 6-8 December 2000, Australian National
University, Canberra Australia.
This paper describes a research project
which aimed to demonstrate the feasibility of
using Fractal Dimension analysis of speed,
occupancy and flow data for automatic
incident detection (AID).