Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Traffic Networks via Neural Networks : Description and Evolution

Sopasakis, Alexandros LU (2020) 6th International Conference on Time Series and Forecasting p.287-301
Abstract
We optimize traffic signal timing sequences for a section of a traffic net- work in order to reduce congestion based on anticipated demand. The system relies on the accuracy of the predicted traffic demand in time and space which is carried out by a neural network. Specifically, we design, train, and evaluate three different neural network models and assert their capability to describe demand from traffic cameras. To train these neural networks we create location specific time series data by approximating vehicle densities from camera images. Each image passes through a cascade of filtering methods and provides a traffic density estimate corresponding to the camera location at that specific time. The system is showcased using real-time... (More)
We optimize traffic signal timing sequences for a section of a traffic net- work in order to reduce congestion based on anticipated demand. The system relies on the accuracy of the predicted traffic demand in time and space which is carried out by a neural network. Specifically, we design, train, and evaluate three different neural network models and assert their capability to describe demand from traffic cameras. To train these neural networks we create location specific time series data by approximating vehicle densities from camera images. Each image passes through a cascade of filtering methods and provides a traffic density estimate corresponding to the camera location at that specific time. The system is showcased using real-time camera images from the traffic network of Goteborg. We specifically test this system in reducing congestion for a small section of the traffic network. To facilitate the learning and resulting prediction we collected images from cameras in that network over a couple of months. We then use the neural network to produce forecasts of traffic demand and adjust the traffic signals within that section. To simulate how congestion will evolve once the traffic signals are adjusted we implement an advanced stochastic model. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
LSTM, GRU, SAE, Traffic signal, Neural network
host publication
Contribution to Statistics : Theory and applications of time series analysis - selected contributions - Theory and applications of time series analysis - selected contributions
editor
Valenzuela, Olga ; Rojas, Fernando ; Herrera, Luis Javier ; Pomares, Héctor and Rojas, Ignacio
edition
1st
pages
14 pages
publisher
Springer
conference name
6th International Conference on Time Series and Forecasting
conference location
Granada, Spain
conference dates
2019-09-25 - 2019-09-27
ISBN
978-3-030-56218-2
978-3-030-56219-9
DOI
10.1007/978-3-030-56219-9_19
language
English
LU publication?
yes
id
28fa5609-12e4-4e25-a670-126349fd5096
date added to LUP
2021-02-02 23:03:39
date last changed
2021-05-06 14:33:29
@inbook{28fa5609-12e4-4e25-a670-126349fd5096,
  abstract     = {{We optimize traffic signal timing sequences for a section of a traffic net- work in order to reduce congestion based on anticipated demand. The system relies on the accuracy of the predicted traffic demand in time and space which is carried out by a neural network. Specifically, we design, train, and evaluate three different neural network models and assert their capability to describe demand from traffic cameras. To train these neural networks we create location specific time series data by approximating vehicle densities from camera images. Each image passes through a cascade of filtering methods and provides a traffic density estimate corresponding to the camera location at that specific time. The system is showcased using real-time camera images from the traffic network of Goteborg. We specifically test this system in reducing congestion for a small section of the traffic network. To facilitate the learning and resulting prediction we collected images from cameras in that network over a couple of months. We then use the neural network to produce forecasts of traffic demand and adjust the traffic signals within that section. To simulate how congestion will evolve once the traffic signals are adjusted we implement an advanced stochastic model.}},
  author       = {{Sopasakis, Alexandros}},
  booktitle    = {{Contribution to Statistics : Theory and applications of time series analysis - selected contributions}},
  editor       = {{Valenzuela, Olga and Rojas, Fernando and Herrera, Luis Javier and Pomares, Héctor and Rojas, Ignacio}},
  isbn         = {{978-3-030-56218-2}},
  keywords     = {{LSTM; GRU; SAE; Traffic signal; Neural network}},
  language     = {{eng}},
  month        = {{11}},
  pages        = {{287--301}},
  publisher    = {{Springer}},
  title        = {{Traffic Networks via Neural Networks : Description and Evolution}},
  url          = {{http://dx.doi.org/10.1007/978-3-030-56219-9_19}},
  doi          = {{10.1007/978-3-030-56219-9_19}},
  year         = {{2020}},
}