Short-Term Traffic Flow Forecasting Method Based on the Data from Video Detectors Using a Neural Network

Teresa Pamuła

doi:10.1007/978-3-642-41647-7_19

Short-Term Traffic Flow Forecasting Method Based on the Data from Video Detectors Using a Neural Network

Teresa Pamuła

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

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

7 Citations (Scopus)

Abstract

The paper presents the development of a short-term forecasting method for determining traffic flow values. The study is based on the data from two video detectors located at the ends of a transit road in the city of Gliwice. The data were recorded 24 h/day for a period of one year. Neural networks (NN) were used in the prediction models. The effects, of the size of a time window and the length of selected data registration, on the learning rate of the nets and on the quality of prediction were studied. Tests were performed using three classes of time series corresponding to: working days, Saturdays and Sundays. The aim of the study was to elaborate an accurate short-term predicting method, which can be used in traffic control systems especially incorporated into modules of Intelligent Transportation Systems (ITS).

Original language	English
Title of host publication	Activities of Transport Telematics - 13th International Conference on Transport Systems Telematics, TST 2013, Selected Papers
Publisher	Springer Verlag
Pages	147-154
Number of pages	8
ISBN (Print)	9783642416460
DOIs	https://doi.org/10.1007/978-3-642-41647-7_19
Publication status	Published - 2013
Event	13th International Conference on Transport Systems Telematics, TST 2013 - Katowice-Ustron, Poland Duration: 23 Oct 2013 → 26 Oct 2013

Publication series

Name	Communications in Computer and Information Science
Volume	395 CCIS
ISSN (Print)	1865-0929

Conference

Conference	13th International Conference on Transport Systems Telematics, TST 2013
Country/Territory	Poland
City	Katowice-Ustron
Period	23/10/13 → 26/10/13

UN SDGs

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

SDG 11 Sustainable Cities and Communities

Keywords

neural network
time series
traffic flow prediction

ASJC Scopus subject areas

General Computer Science
General Mathematics

Access to Document

10.1007/978-3-642-41647-7_19

Cite this

Pamuła, T. (2013). Short-Term Traffic Flow Forecasting Method Based on the Data from Video Detectors Using a Neural Network. In Activities of Transport Telematics - 13th International Conference on Transport Systems Telematics, TST 2013, Selected Papers (pp. 147-154). (Communications in Computer and Information Science; Vol. 395 CCIS). Springer Verlag. https://doi.org/10.1007/978-3-642-41647-7_19

@inproceedings{2fbd8e6f60a14f7e900c3902c2aaed0d,

title = "Short-Term Traffic Flow Forecasting Method Based on the Data from Video Detectors Using a Neural Network",

abstract = "The paper presents the development of a short-term forecasting method for determining traffic flow values. The study is based on the data from two video detectors located at the ends of a transit road in the city of Gliwice. The data were recorded 24 h/day for a period of one year. Neural networks (NN) were used in the prediction models. The effects, of the size of a time window and the length of selected data registration, on the learning rate of the nets and on the quality of prediction were studied. Tests were performed using three classes of time series corresponding to: working days, Saturdays and Sundays. The aim of the study was to elaborate an accurate short-term predicting method, which can be used in traffic control systems especially incorporated into modules of Intelligent Transportation Systems (ITS).",

keywords = "neural network, time series, traffic flow prediction",

author = "Teresa Pamu{\l}a",

year = "2013",

doi = "10.1007/978-3-642-41647-7\_19",

language = "English",

isbn = "9783642416460",

series = "Communications in Computer and Information Science",

publisher = "Springer Verlag",

pages = "147--154",

booktitle = "Activities of Transport Telematics - 13th International Conference on Transport Systems Telematics, TST 2013, Selected Papers",

address = "Germany",

note = "13th International Conference on Transport Systems Telematics, TST 2013 ; Conference date: 23-10-2013 Through 26-10-2013",

}

Pamuła, T 2013, Short-Term Traffic Flow Forecasting Method Based on the Data from Video Detectors Using a Neural Network. in Activities of Transport Telematics - 13th International Conference on Transport Systems Telematics, TST 2013, Selected Papers. Communications in Computer and Information Science, vol. 395 CCIS, Springer Verlag, pp. 147-154, 13th International Conference on Transport Systems Telematics, TST 2013, Katowice-Ustron, Poland, 23/10/13. https://doi.org/10.1007/978-3-642-41647-7_19

Short-Term Traffic Flow Forecasting Method Based on the Data from Video Detectors Using a Neural Network. / Pamuła, Teresa.
Activities of Transport Telematics - 13th International Conference on Transport Systems Telematics, TST 2013, Selected Papers. Springer Verlag, 2013. p. 147-154 (Communications in Computer and Information Science; Vol. 395 CCIS).

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

TY - GEN

T1 - Short-Term Traffic Flow Forecasting Method Based on the Data from Video Detectors Using a Neural Network

AU - Pamuła, Teresa

PY - 2013

Y1 - 2013

N2 - The paper presents the development of a short-term forecasting method for determining traffic flow values. The study is based on the data from two video detectors located at the ends of a transit road in the city of Gliwice. The data were recorded 24 h/day for a period of one year. Neural networks (NN) were used in the prediction models. The effects, of the size of a time window and the length of selected data registration, on the learning rate of the nets and on the quality of prediction were studied. Tests were performed using three classes of time series corresponding to: working days, Saturdays and Sundays. The aim of the study was to elaborate an accurate short-term predicting method, which can be used in traffic control systems especially incorporated into modules of Intelligent Transportation Systems (ITS).

AB - The paper presents the development of a short-term forecasting method for determining traffic flow values. The study is based on the data from two video detectors located at the ends of a transit road in the city of Gliwice. The data were recorded 24 h/day for a period of one year. Neural networks (NN) were used in the prediction models. The effects, of the size of a time window and the length of selected data registration, on the learning rate of the nets and on the quality of prediction were studied. Tests were performed using three classes of time series corresponding to: working days, Saturdays and Sundays. The aim of the study was to elaborate an accurate short-term predicting method, which can be used in traffic control systems especially incorporated into modules of Intelligent Transportation Systems (ITS).

KW - neural network

KW - time series

KW - traffic flow prediction

UR - https://www.scopus.com/pages/publications/84904691338

U2 - 10.1007/978-3-642-41647-7_19

DO - 10.1007/978-3-642-41647-7_19

M3 - Conference contribution

AN - SCOPUS:84904691338

SN - 9783642416460

T3 - Communications in Computer and Information Science

SP - 147

EP - 154

BT - Activities of Transport Telematics - 13th International Conference on Transport Systems Telematics, TST 2013, Selected Papers

PB - Springer Verlag

T2 - 13th International Conference on Transport Systems Telematics, TST 2013

Y2 - 23 October 2013 through 26 October 2013

ER -

Short-Term Traffic Flow Forecasting Method Based on the Data from Video Detectors Using a Neural Network

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this