Optimizing Traffic Network around Grade Crossing for the Case of AALRT
No Thumbnail Available
Date
2016-06
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
The existing public transport system in Addis Ababa is critically insufficient to provide service
for the existing travel demand. Public transportation is one and the most important means of
easing traffic congestion for it makes roads work better by reducing the number of vehicles on
the road. This shows that a great concern should go towards the expansion of high- capacity
public transportation system like introduction of light rail, heavy rail, road bus transit, and high
occupancy vehicles lanes, which coupled with better management of the existing road network
and traffic management. We need therefore to have a clearly defined transport management
technology to challenge the mobility issues of the city. Grade Crossing is a location where a
public highway, road, street, or private roadway, including associated sidewalks, and pathways,
crosses railroad tracks at grade (same level as the street).The aim of this thesis is to encourage
grade crossing safety and reduce highway traffic delay. The safety of grade crossing can be
promoted by removing those vehicles detected on the railroad tracks before the arrival of trains
using CCTV camera by image processing technology. Reduce highway traffic delay by proper
managing the phase sequence of the intersection. A system model is proposed and developing
with the system. The optimization will be implemented into two steps. The first step, the delay
function is approximated and represented by artificial neural network. Secondly optimization
will be applied based on Levenberg-Marquardt optimization.
We use different approach, instead of protecting grade crossing manually and showing the
hostility to the highway drivers, we could develop an advanced traffic management system smart
enough to control the traffic near grade crossings. In such a system, we could incorporate grade
crossing information into traffic control and prevent the queue from backing onto the railroad
tracks. Preemption of the traffic signal at/near a grade crossing is such an alternative to target
safety improvement. Artificial neural network is design for both train arrival time at grade
crossing and forecasting of traffic signal phase length at intersection. MATLAB programing is
applied for the designs simulation. From the simulation result the network is optimized by
decreasing MSE of train arrival time and traffic signal phase length prediction by 2.2696x10-19
and 8.338x10-9 respectively. Image processing is applied for obstacle detections on grade
crossing by the concept of image segmented in matrix form.
Description
Keywords
Bistatic radar, artificial neural network, transition preemptions strategy, image processing, MSE, CCTV, grade crossing