Automated incident detection and alternative path planning form important a
ctivities within a modern expressway traffic management system which aims t
o ensure a smooth flow of traffic along expressways. This is done by adopti
ng efficient technologies and processes that can be directly applied for th
e automated detection of non-recurrent congestion, the formulation of respo
nse strategies, and the use of management techniques to suggest alternative
routes to the road-users, resulting in significant overall reductions in b
oth congestion and inconvenience to motorists. A delicate balance has to be
struck here between the incident detection rate and the false-alarm rate.
This paper presents the development of a hybrid artificial intelligence tec
hnique for automatically detecting incidents on a traffic network. The over
all framework, algorithm development, implementation and evaluation of this
hybrid fuzzy-logic genetic-algorithm technique are discussed in the paper.
A cascaded framework of 11 fuzzy controllers takes in traffic indices such
as occupancy and volume, to detect incidents along an expressway in Califo
rnia. The flexible and robust nature of the developed fuzzy controller allo
ws it to model functions of arbitrary complexity, while at the same time be
ing inherently highly tolerant of imprecise data. The maximizing capabiliti
es of genetic algorithms, on the other hand, enable the fuzzy design parame
ters to be optimized to achieve optimal performance. The results obtained f
or the traffic network give a high detection rate of 70.0%, while giving a
low false-alarm rate of 0.83%. A comparison between this approach and four
other incident-detection algorithms demonstrates the superiority of this ap
proach. (C) 2000 Elsevier Science Ltd. All rights reserved.