Information Technology Reference
In-Depth Information
A Fuzzy Logic Modeling Approach to Assess
the Speed Limit Suitability in Urban Street Networks
Yaser E. Hawas and Md. Bayzid Khan
Roadway, Transportation and Traffic Safety Research Center, UAE University,
Al Ain, United Arab Emirates
{y.hawas@uaeu.ac.ae}
Abstract.
This paper discusses the development of fuzzy logic model for esti-
mating the 85
th
percentile speed of urban roads. Spot speed survey was con-
ducted on four randomly selected urban road segments for a typical weekday
and a weekend. The considered road segment attribute data are length of the
road segment, number of access points/intersecting links, number of pedestrian
crossings, number of lanes, hourly traffic volume, hourly pedestrian volume and
current posted speed limits of the selected roads. Such attribute data were col-
lected and used as input variables in the model. Two models for weekday and
weekend were developed based on the field survey data. Both models were ca-
librated using the neuro-fuzzy technique for optimizing the fuzzy logic model
(FLM) parameters. Analyses of estimated results show that the FLM can esti-
mate the 85
th
percentile speed to a reasonable level.
Keywords:
85
th
Percentile Speed, Posted Speed Limit, Fuzzy Logic,
Neuro-fuzzy Training.
1
Introduction
Determining a safer posted speed limit for any given roads/links is one of the major
challenges for the researchers and professionals all around the world. Many studies
tried to identify the safer speed limit for a road [1-3]. Setting a speed limit is a multi-
criteria task. Many road and roadside factors such as the road alignment, section
length, traffic volume, pedestrian volume, current speed limit, number of lanes,
weather condition, time of the day, law enforcement, purpose and length of the trip,
vehicles' characteristics are to be incorporated. [4-5]. Setting the speed limits also
requires understanding the drivers' characteristics and their driving pattern. As such,
most of the studies suggested the 85
th
percentile of the operating speed to be set as the
posted speed limit [6].
Studies showed that the chances of involving in a crash is least at 85
th
the percen-
tile traffic speed [1], [7].
Developing a model to estimate the 85
th
percentile speed by incorporating all the
factors is quite challenging. The individual driver's operating speed depends on indi-
vidual driver's perception about all of the above mentioned factors. For a given road
characteristics, every driver may choose different operating speed. Therefore, it is
very important to develop a method to estimate the 85th percentile speed which will
also address such uncertain choice behavior.
