Junction Traffic Prediction, Using Adjacent Junction Traffic Data, Based on Neural Networks

Teresa Pamuła; Wiesław Pamuła

doi:10.1007/978-3-319-99477-2_5

Junction Traffic Prediction, Using Adjacent Junction Traffic Data, Based on Neural Networks

Teresa Pamuła
, Wiesław Pamuła

Department of Transport Systems, Traffic Engineering and Logistics (RT/RT4)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

The paper discusses the problem of substitution of traffic data, used for prediction of traffic flows at a junction, with data from an adjacent junction. Such a case arises when the measuring resources at the junction malfunction. Neural networks based approach is used for forecasting traffic flows. Solutions incorporating a multilayer perceptron (MLP) network, a cascade forward network (CFN) and a deep learning network (DLN) with autoencoders are used for evaluating the prediction performance. The elaborated designs are validated using a data set of traffic flow measurements comprising over 15 thousand measurements collected in a period of over six months. Results prove that substituting data from an adjacent junction is justified for predicting traffic flows in case of malfunctioning measuring resources.

Original language	English
Title of host publication	Integration as Solution for Advanced Smart Urban Transport Systems - 15th Scientific and Technical Conference “Transport Systems. Theory and Practice 2018”, Selected Papers
Editors	Grzegorz Sierpinski
Publisher	Springer Verlag
Pages	49-57
Number of pages	9
ISBN (Print)	9783319994765
DOIs	https://doi.org/10.1007/978-3-319-99477-2_5
Publication status	Published - 2019
Event	15th Scientific and Technical Conference on Transport Systems Theory and Practice, TSTP 2018 - Katowice, Poland Duration: 17 Sept 2018 → 19 Sept 2018

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	844
ISSN (Print)	2194-5357

Conference

Conference	15th Scientific and Technical Conference on Transport Systems Theory and Practice, TSTP 2018
Country/Territory	Poland
City	Katowice
Period	17/09/18 → 19/09/18

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Keywords

Intelligent transport system
Neural network structure
Traffic flow prediction

ASJC Scopus subject areas

Control and Systems Engineering
General Computer Science

Access to Document

10.1007/978-3-319-99477-2_5

Cite this

Pamuła, T., & Pamuła, W. (2019). Junction Traffic Prediction, Using Adjacent Junction Traffic Data, Based on Neural Networks. In G. Sierpinski (Ed.), Integration as Solution for Advanced Smart Urban Transport Systems - 15th Scientific and Technical Conference “Transport Systems. Theory and Practice 2018”, Selected Papers (pp. 49-57). (Advances in Intelligent Systems and Computing; Vol. 844). Springer Verlag. https://doi.org/10.1007/978-3-319-99477-2_5

Pamuła, Teresa ; Pamuła, Wiesław. / Junction Traffic Prediction, Using Adjacent Junction Traffic Data, Based on Neural Networks. Integration as Solution for Advanced Smart Urban Transport Systems - 15th Scientific and Technical Conference “Transport Systems. Theory and Practice 2018”, Selected Papers. editor / Grzegorz Sierpinski. Springer Verlag, 2019. pp. 49-57 (Advances in Intelligent Systems and Computing).

@inproceedings{9d7bb18f29af44d2985fc1e254cbd5be,

title = "Junction Traffic Prediction, Using Adjacent Junction Traffic Data, Based on Neural Networks",

abstract = "The paper discusses the problem of substitution of traffic data, used for prediction of traffic flows at a junction, with data from an adjacent junction. Such a case arises when the measuring resources at the junction malfunction. Neural networks based approach is used for forecasting traffic flows. Solutions incorporating a multilayer perceptron (MLP) network, a cascade forward network (CFN) and a deep learning network (DLN) with autoencoders are used for evaluating the prediction performance. The elaborated designs are validated using a data set of traffic flow measurements comprising over 15 thousand measurements collected in a period of over six months. Results prove that substituting data from an adjacent junction is justified for predicting traffic flows in case of malfunctioning measuring resources.",

keywords = "Intelligent transport system, Neural network structure, Traffic flow prediction",

author = "Teresa Pamu{\l}a and Wies{\l}aw Pamu{\l}a",

note = "Publisher Copyright: {\textcopyright} 2019, Springer Nature Switzerland AG.; 15th Scientific and Technical Conference on Transport Systems Theory and Practice, TSTP 2018 ; Conference date: 17-09-2018 Through 19-09-2018",

year = "2019",

doi = "10.1007/978-3-319-99477-2\_5",

language = "English",

isbn = "9783319994765",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Verlag",

pages = "49--57",

editor = "Grzegorz Sierpinski",

booktitle = "Integration as Solution for Advanced Smart Urban Transport Systems - 15th Scientific and Technical Conference {\textquotedblleft}Transport Systems. Theory and Practice 2018{\textquotedblright}, Selected Papers",

address = "Germany",

}

Pamuła, T & Pamuła, W 2019, Junction Traffic Prediction, Using Adjacent Junction Traffic Data, Based on Neural Networks. in G Sierpinski (ed.), Integration as Solution for Advanced Smart Urban Transport Systems - 15th Scientific and Technical Conference “Transport Systems. Theory and Practice 2018”, Selected Papers. Advances in Intelligent Systems and Computing, vol. 844, Springer Verlag, pp. 49-57, 15th Scientific and Technical Conference on Transport Systems Theory and Practice, TSTP 2018, Katowice, Poland, 17/09/18. https://doi.org/10.1007/978-3-319-99477-2_5

Junction Traffic Prediction, Using Adjacent Junction Traffic Data, Based on Neural Networks. / Pamuła, Teresa; Pamuła, Wiesław.
Integration as Solution for Advanced Smart Urban Transport Systems - 15th Scientific and Technical Conference “Transport Systems. Theory and Practice 2018”, Selected Papers. ed. / Grzegorz Sierpinski. Springer Verlag, 2019. p. 49-57 (Advances in Intelligent Systems and Computing; Vol. 844).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Junction Traffic Prediction, Using Adjacent Junction Traffic Data, Based on Neural Networks

AU - Pamuła, Teresa

AU - Pamuła, Wiesław

PY - 2019

Y1 - 2019

N2 - The paper discusses the problem of substitution of traffic data, used for prediction of traffic flows at a junction, with data from an adjacent junction. Such a case arises when the measuring resources at the junction malfunction. Neural networks based approach is used for forecasting traffic flows. Solutions incorporating a multilayer perceptron (MLP) network, a cascade forward network (CFN) and a deep learning network (DLN) with autoencoders are used for evaluating the prediction performance. The elaborated designs are validated using a data set of traffic flow measurements comprising over 15 thousand measurements collected in a period of over six months. Results prove that substituting data from an adjacent junction is justified for predicting traffic flows in case of malfunctioning measuring resources.

AB - The paper discusses the problem of substitution of traffic data, used for prediction of traffic flows at a junction, with data from an adjacent junction. Such a case arises when the measuring resources at the junction malfunction. Neural networks based approach is used for forecasting traffic flows. Solutions incorporating a multilayer perceptron (MLP) network, a cascade forward network (CFN) and a deep learning network (DLN) with autoencoders are used for evaluating the prediction performance. The elaborated designs are validated using a data set of traffic flow measurements comprising over 15 thousand measurements collected in a period of over six months. Results prove that substituting data from an adjacent junction is justified for predicting traffic flows in case of malfunctioning measuring resources.

KW - Intelligent transport system

KW - Neural network structure

KW - Traffic flow prediction

UR - https://www.scopus.com/pages/publications/85053181990

U2 - 10.1007/978-3-319-99477-2_5

DO - 10.1007/978-3-319-99477-2_5

M3 - Conference contribution

AN - SCOPUS:85053181990

SN - 9783319994765

T3 - Advances in Intelligent Systems and Computing

SP - 49

EP - 57

BT - Integration as Solution for Advanced Smart Urban Transport Systems - 15th Scientific and Technical Conference “Transport Systems. Theory and Practice 2018”, Selected Papers

A2 - Sierpinski, Grzegorz

PB - Springer Verlag

T2 - 15th Scientific and Technical Conference on Transport Systems Theory and Practice, TSTP 2018

Y2 - 17 September 2018 through 19 September 2018

ER -

Pamuła T, Pamuła W. Junction Traffic Prediction, Using Adjacent Junction Traffic Data, Based on Neural Networks. In Sierpinski G, editor, Integration as Solution for Advanced Smart Urban Transport Systems - 15th Scientific and Technical Conference “Transport Systems. Theory and Practice 2018”, Selected Papers. Springer Verlag. 2019. p. 49-57. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-319-99477-2_5

Junction Traffic Prediction, Using Adjacent Junction Traffic Data, Based on Neural Networks

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this