Short term traffic speed prediction using different feature sets and sensor clusters

Halil Gülaçar; Yusuf Yaslan; Sema F. Oktuǧ

doi:10.1109/NOMS.2016.7503000

Short term traffic speed prediction using different feature sets and sensor clusters

Halil Gülaçar, Yusuf Yaslan, Sema F. Oktuǧ

Department of Computer Engineering

Istanbul Technical University

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

7 Citations (Scopus)

Abstract

Accurate short term traffic speed prediction has been one of the most important issues of Intelligent Traffic Systems. In literature there have been many works that apply prediction models on few amounts of sensors' data for a short time training and test period. Unlike most of the previous works, in this paper we used 122 speed sensors' data from Istanbul that was collected from 1st January to 31st December 2014. We extracted four different feature sets for regression algorithms. Then we clustered the sensors into different groups and trained a model for each group. Prediction results are obtained by using decision tree and KNN based regression algorithms. Experimental results show that KNN based regression algorithm generally outperforms decision trees and training a single KNN model for each sensor is better than training a general model for all sensors. On the other hand, incorporating weather data doesn't help to improve the performance beyond our expectations.

Original language	English
Title of host publication	Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium
Editors	Sema Oktug Badonnel, Mehmet Ulema, Cicek Cavdar, Lisandro Zambenedetti Granville, Carlos Raniery P. dos Santos
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1265-1268
Number of pages	4
ISBN (Electronic)	9781509002238
DOIs	https://doi.org/10.1109/NOMS.2016.7503000
Publication status	Published - 30 Jun 2016
Event	2016 IEEE/IFIP Network Operations and Management Symposium, NOMS 2016 - Istanbul, Turkey Duration: 25 Apr 2016 → 29 Apr 2016

Publication series

Name	Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium

Conference

Conference	2016 IEEE/IFIP Network Operations and Management Symposium, NOMS 2016
Country/Territory	Turkey
City	Istanbul
Period	25/04/16 → 29/04/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

regression
traffic prediction
traffic speed

UN SDGs

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

Access to Document

10.1109/NOMS.2016.7503000

Cite this

Gülaçar, H., Yaslan, Y., & Oktuǧ, S. F. (2016). Short term traffic speed prediction using different feature sets and sensor clusters. In S. O. Badonnel, M. Ulema, C. Cavdar, L. Z. Granville, & C. R. P. dos Santos (Eds.), Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium (pp. 1265-1268). Article 7503000 (Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NOMS.2016.7503000

Gülaçar, Halil ; Yaslan, Yusuf ; Oktuǧ, Sema F. / Short term traffic speed prediction using different feature sets and sensor clusters. Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium. editor / Sema Oktug Badonnel ; Mehmet Ulema ; Cicek Cavdar ; Lisandro Zambenedetti Granville ; Carlos Raniery P. dos Santos. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1265-1268 (Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium).

@inproceedings{4be4a07636f14abcaedf62a09323aebc,

title = "Short term traffic speed prediction using different feature sets and sensor clusters",

abstract = "Accurate short term traffic speed prediction has been one of the most important issues of Intelligent Traffic Systems. In literature there have been many works that apply prediction models on few amounts of sensors' data for a short time training and test period. Unlike most of the previous works, in this paper we used 122 speed sensors' data from Istanbul that was collected from 1st January to 31st December 2014. We extracted four different feature sets for regression algorithms. Then we clustered the sensors into different groups and trained a model for each group. Prediction results are obtained by using decision tree and KNN based regression algorithms. Experimental results show that KNN based regression algorithm generally outperforms decision trees and training a single KNN model for each sensor is better than training a general model for all sensors. On the other hand, incorporating weather data doesn't help to improve the performance beyond our expectations.",

keywords = "regression, traffic prediction, traffic speed",

author = "Halil G{\"u}la{\c c}ar and Yusuf Yaslan and Oktuǧ, {Sema F.}",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 IEEE/IFIP Network Operations and Management Symposium, NOMS 2016 ; Conference date: 25-04-2016 Through 29-04-2016",

year = "2016",

month = jun,

day = "30",

doi = "10.1109/NOMS.2016.7503000",

language = "English",

series = "Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1265--1268",

editor = "Badonnel, {Sema Oktug} and Mehmet Ulema and Cicek Cavdar and Granville, {Lisandro Zambenedetti} and {dos Santos}, {Carlos Raniery P.}",

booktitle = "Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium",

address = "United States",

}

Gülaçar, H, Yaslan, Y & Oktuǧ, SF 2016, Short term traffic speed prediction using different feature sets and sensor clusters. in SO Badonnel, M Ulema, C Cavdar, LZ Granville & CRP dos Santos (eds), Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium., 7503000, Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium, Institute of Electrical and Electronics Engineers Inc., pp. 1265-1268, 2016 IEEE/IFIP Network Operations and Management Symposium, NOMS 2016, Istanbul, Turkey, 25/04/16. https://doi.org/10.1109/NOMS.2016.7503000

Short term traffic speed prediction using different feature sets and sensor clusters. / Gülaçar, Halil; Yaslan, Yusuf; Oktuǧ, Sema F.
Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium. ed. / Sema Oktug Badonnel; Mehmet Ulema; Cicek Cavdar; Lisandro Zambenedetti Granville; Carlos Raniery P. dos Santos. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1265-1268 7503000 (Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium).

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

TY - GEN

T1 - Short term traffic speed prediction using different feature sets and sensor clusters

AU - Gülaçar, Halil

AU - Yaslan, Yusuf

AU - Oktuǧ, Sema F.

PY - 2016/6/30

Y1 - 2016/6/30

N2 - Accurate short term traffic speed prediction has been one of the most important issues of Intelligent Traffic Systems. In literature there have been many works that apply prediction models on few amounts of sensors' data for a short time training and test period. Unlike most of the previous works, in this paper we used 122 speed sensors' data from Istanbul that was collected from 1st January to 31st December 2014. We extracted four different feature sets for regression algorithms. Then we clustered the sensors into different groups and trained a model for each group. Prediction results are obtained by using decision tree and KNN based regression algorithms. Experimental results show that KNN based regression algorithm generally outperforms decision trees and training a single KNN model for each sensor is better than training a general model for all sensors. On the other hand, incorporating weather data doesn't help to improve the performance beyond our expectations.

AB - Accurate short term traffic speed prediction has been one of the most important issues of Intelligent Traffic Systems. In literature there have been many works that apply prediction models on few amounts of sensors' data for a short time training and test period. Unlike most of the previous works, in this paper we used 122 speed sensors' data from Istanbul that was collected from 1st January to 31st December 2014. We extracted four different feature sets for regression algorithms. Then we clustered the sensors into different groups and trained a model for each group. Prediction results are obtained by using decision tree and KNN based regression algorithms. Experimental results show that KNN based regression algorithm generally outperforms decision trees and training a single KNN model for each sensor is better than training a general model for all sensors. On the other hand, incorporating weather data doesn't help to improve the performance beyond our expectations.

KW - regression

KW - traffic prediction

KW - traffic speed

UR - http://www.scopus.com/inward/record.url?scp=84979779784&partnerID=8YFLogxK

U2 - 10.1109/NOMS.2016.7503000

DO - 10.1109/NOMS.2016.7503000

M3 - Conference contribution

AN - SCOPUS:84979779784

T3 - Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium

SP - 1265

EP - 1268

BT - Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium

A2 - Badonnel, Sema Oktug

A2 - Ulema, Mehmet

A2 - Cavdar, Cicek

A2 - Granville, Lisandro Zambenedetti

A2 - dos Santos, Carlos Raniery P.

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 IEEE/IFIP Network Operations and Management Symposium, NOMS 2016

Y2 - 25 April 2016 through 29 April 2016

ER -

Gülaçar H, Yaslan Y, Oktuǧ SF. Short term traffic speed prediction using different feature sets and sensor clusters. In Badonnel SO, Ulema M, Cavdar C, Granville LZ, dos Santos CRP, editors, Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1265-1268. 7503000. (Proceedings of the NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium). doi: 10.1109/NOMS.2016.7503000

Short term traffic speed prediction using different feature sets and sensor clusters

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this