Congestion prediction on motorways: a comparative analysis

G. Huisken; M.F.A.M. van Maarseveen

Congestion prediction on motorways: a comparative analysis

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

27 Downloads (Pure)

Abstract

The paper reports on the evaluation of the performance of various short-term congestion prediction methods, i.e. multi-linear regression, time series analysis, multi-layer perceptrons, radial basis function networks, self-organising systems, and fuzzy logic. Data were gathered through dual induction loops on a A10 motorway section in the Netherlands during a fourweek period. The data consist of 1 minute aggregated time bins of volume, occupancy, speed, and both a reliability and a congestion indicator. The method's results are similar, except for multi-linear regression. Self-organising systems were omitted due to huge error production.

Original language	English
Title of host publication	From Vision to Reality
Subtitle of host publication	Proceedings of the 7th World Congress on Intelligent Transportation Systems, 6-9 November 2000, on CD-ROM
Place of Publication	Turin, Italy
Number of pages	7
Publication status	Published - 2000
Event	7th World Congress on Intelligent Transportation Systems 2000 - Turin, Italy Duration: 6 Nov 2000 → 9 Nov 2000 Conference number: 7

Conference

Conference	7th World Congress on Intelligent Transportation Systems 2000
Country/Territory	Italy
City	Turin
Period	6/11/00 → 9/11/00

Keywords

ADLIB-ART-853
PGM

Access to Document

Huisken2000congestionFinal published version, 77 KB

Cite this

@inproceedings{dd2d46d2bb904b4c97994a22d84f506e,

title = "Congestion prediction on motorways: a comparative analysis",

abstract = "The paper reports on the evaluation of the performance of various short-term congestion prediction methods, i.e. multi-linear regression, time series analysis, multi-layer perceptrons, radial basis function networks, self-organising systems, and fuzzy logic. Data were gathered through dual induction loops on a A10 motorway section in the Netherlands during a fourweek period. The data consist of 1 minute aggregated time bins of volume, occupancy, speed, and both a reliability and a congestion indicator. The method's results are similar, except for multi-linear regression. Self-organising systems were omitted due to huge error production.",

keywords = "ADLIB-ART-853, PGM",

author = "G. Huisken and {van Maarseveen}, M.F.A.M.",

year = "2000",

language = "English",

booktitle = "From Vision to Reality",

note = "7th World Congress on Intelligent Transportation Systems 2000 ; Conference date: 06-11-2000 Through 09-11-2000",

}

TY - GEN

T1 - Congestion prediction on motorways

T2 - 7th World Congress on Intelligent Transportation Systems 2000

AU - Huisken, G.

AU - van Maarseveen, M.F.A.M.

N1 - Conference code: 7

PY - 2000

Y1 - 2000

N2 - The paper reports on the evaluation of the performance of various short-term congestion prediction methods, i.e. multi-linear regression, time series analysis, multi-layer perceptrons, radial basis function networks, self-organising systems, and fuzzy logic. Data were gathered through dual induction loops on a A10 motorway section in the Netherlands during a fourweek period. The data consist of 1 minute aggregated time bins of volume, occupancy, speed, and both a reliability and a congestion indicator. The method's results are similar, except for multi-linear regression. Self-organising systems were omitted due to huge error production.

AB - The paper reports on the evaluation of the performance of various short-term congestion prediction methods, i.e. multi-linear regression, time series analysis, multi-layer perceptrons, radial basis function networks, self-organising systems, and fuzzy logic. Data were gathered through dual induction loops on a A10 motorway section in the Netherlands during a fourweek period. The data consist of 1 minute aggregated time bins of volume, occupancy, speed, and both a reliability and a congestion indicator. The method's results are similar, except for multi-linear regression. Self-organising systems were omitted due to huge error production.

KW - ADLIB-ART-853

KW - PGM

UR - https://ezproxy2.utwente.nl/login?url=https://webapps.itc.utwente.nl/library/2000/conf/vanmaarseveen_con.pdf

M3 - Conference contribution

BT - From Vision to Reality

CY - Turin, Italy

Y2 - 6 November 2000 through 9 November 2000

ER -

Congestion prediction on motorways: a comparative analysis

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this