Safety

This study attempts to develop an arterial incident detection model by applying an
Artificial Neural Network (ANN) with simulation data. A section of the US-1 corridor in Miami-
Dade County, Florida was selected as the study area and coded in the CORSIM microscopic
simulation model. Two data sets were generated via CORSIM simulation for model
development and assessment. Multiple ANN models were designed for various scenarios. The
model performances were evaluated using the selected measures of effectiveness (MOE),
including detection rate (DR) and false alarm rate (FAR). The results showed that the ANN
models in general could detect arterial incidents with a high DR of 90-95% and an acceptable
FAR of lower than 4%. The study also identified some preferred features in the design of ANN
incident detection models for this application. These include the detector configuration scheme,
the selection of model input features, and the employment of data from previous cycles.

DMJM Harris

Florida International University

Presented at the 15th World Congress on Intelligent Transport Systems, November 16-20, 2008, New York, New York

Growing concern over traffic safety has led to research efforts directed towards predicting
freeway accidents in ATMS (advanced traffic management systems) environment. This study
aims at developing accident likelihood prediction model using real-time traffic flow variables
and rain data potentially associated with accident occurrence. Archived loop detector and rain
data and historical accident data have been used to calibrate the model. This model can be
implemented using on-line loop and rain data to identify high accident potential in real-time.
Principal Component Analysis (PCA) and Logistic Regression have been used to estimate a
weather model that determines a rain index based on the rain readings at the weather station in
the proximity of the freeway. A logit model has also been used to model the accident potential
based on traffic loop data and the rain index. The 5-minute average occupancy and standard
deviation of volume observed at the downstream station, and the 5-minute coefficient of
variation in speed at the station closest to the accident, all during 5-10 minutes prior to the
accident occurrence along with the rain index have been found to affect the accident occurrence
most significantly.

University of Central Florida

Presented at the 12th World Congress on Intelligent Transport Systems, November 6-10, 2005, San Francisco, California

In this paper, floating car data (FCD) are utilized to detect traffic congestion which happened
around the intersections in city road network. The actual real-time data of the city of Ningbo,
China, are presented to describe the characteristic of traffic  flow when congestion appears.
Then the basic traffic jam detection algorithm is developed. According to the detection results,
the traffic management center (TMC) can position the traffic congestion accurately in short
time. The validity of this traffic congestion detection method is proved by video surveillance
system of central Ningbo city  and the detecting performances are evaluated under different
traffic congested conditions.

Ningbo YiChuang Information Technology Co.

The Research Center for Software Engineering Technology of Anhui Province

College of Computer Science and Technology, Zhejiang University

The Road and Traffic Management Bureau of Anhui Province

Presented at the ITS America Annual Conference and Exposition,November 16-20, 2008, New York, New York

Winter maintenance operations, including snow removal, are subject to increased risk by conditions such as total visual whiteout, low traction on wet or icy pavement, drifting snow and roadways completely covered by snow. Additional hazards are posed by objects buried in or obscured by snow. Furthermore, snowplow operators often lack important visual cues as to their position on the roadway due to accumulations of snow from previous plowing activities. In many of the colder, mountainous states, snowplows that run off the roadway have greater potential for equipment damage and personal injury due to the mountainous terrain in which much of the snow removal operations take place. The opportunity to address these risks with Advanced Vehicle Control and Safety Systems (AVCSS) technologies was the impetus for the Advanced Snowplow Development and Demonstration project. These AVCSS technologies have been incorporated into the United States Department of Transportation.s (USDOT) Intelligent Vehicle Initiative (IVI) program.

The main purpose of the Advanced Snowplow Development and Demonstration project was to design, integrate and test AVCSS technologies on snowplow maintenance equipment. This phase of the project has attempted to assess potential benefits associated with combining conventional snowplow operations with Intelligent Vehicle (IV) technologies in terms of improved efficiency and safety on rural roadway segments in California and Arizona. A prototype snowplow was equipped with lateral lane indication and forward collision warning systems. The subsequent evaluation attempted to determine the effectiveness of the advanced technology system in terms of safety and operational efficiency, as well as perceived benefits or concerns expressed by the snowplow operators. In addition, the accuracy and reliability of the system was examined.

The results of this initial evaluation will first, provide the results necessary to determine the feasibility of AVCSS in improving safety and efficiency of snowplow removal and second, help establish a methodology for future AVCSS evaluation projects.

Montana State University – Bozeman: Western Transportation Institute

Presented at the 10th ITS Annual Conference and Exposition, May 1-4, 2000 Boston, MA

A vehicle approach warning system (VAWS) provides the drivers of vehicles approaching a
sharp turn with the information about vehicles approaching the same turn from the opposite
end. This paper describes an IEEE 802.15.4-based hierarchical sensor network model for the
VAWS. In this network model, a tree-structured topology, that can prolong the lifetime of
network, is formed in a self-organizing manner by the topology control protocol. A simple,
but efficient routing protocol transports data packets generated from the sensor nodes to the
base station which then forwards it to a display processor. These protocols are designed as a
network layer extension to the IEEE 802.15.4 PHY/MAC. Simulation results shows that the
proposed joint topology control and routing metric combined with the network model
achieves a high-level performance in terms of both energy efficiency and throughput
simultaneously.

Kwangwoon University

Samsung Thales Co., Ltd.

Presented at the 15th World Congress on Intelligent Transport Systems, November 16-20, 2008, New York, New York