A hybrid model for forecasting local traffic parameters

Heidrun Belzner; Klaus Bogenberger; Ronald Kates

doi:10.1016/S1474-6670(17)32431-X

A hybrid model for forecasting local traffic parameters

Heidrun Belzner, Klaus Bogenberger, Ronald Kates

BMW AG

Research output: Contribution to journal › Conference article › peer-review

Abstract

Predicting traffic is certainly one of the greatest challenges facing current traffic engineering research. The work presented here focuses on the prediction of local traffic parameters such as the local mean speed aggregated over short periods such as one minute. For this purpose a new hybrid model comprising an ARIMA¹ model and a neural network has been developed and validated with real traffic data. This model has been evaluated and compared with conventional methods of traffic prediction using independent real test data. It was found that the new hybrid model produces more accurate and more reliable results than conventional methods.

Original language	English
Pages (from-to)	269-273
Number of pages	5
Journal	IFAC Proceedings Volumes (IFAC-PapersOnline)
Volume	36
Issue number	14
DOIs	https://doi.org/10.1016/S1474-6670(17)32431-X
State	Published - 2003
Externally published	Yes
Event	10th IFAC Symposium on Control in Transportation Systems 2003 - Tokyo, Japan Duration: 4 Aug 2003 → 6 Aug 2003

Keywords

ARIMA models
Backpropagation algorithms
Forecasts
Neural networks
Stochastic realization

Access to Document

10.1016/S1474-6670(17)32431-X

Cite this

@article{8ed748fe23294ce6b720362ce459826c,

title = "A hybrid model for forecasting local traffic parameters",

abstract = "Predicting traffic is certainly one of the greatest challenges facing current traffic engineering research. The work presented here focuses on the prediction of local traffic parameters such as the local mean speed aggregated over short periods such as one minute. For this purpose a new hybrid model comprising an ARIMA1 model and a neural network has been developed and validated with real traffic data. This model has been evaluated and compared with conventional methods of traffic prediction using independent real test data. It was found that the new hybrid model produces more accurate and more reliable results than conventional methods.",

keywords = "ARIMA models, Backpropagation algorithms, Forecasts, Neural networks, Stochastic realization",

author = "Heidrun Belzner and Klaus Bogenberger and Ronald Kates",

note = "Publisher Copyright: Copyright {\textcopyright} IFAC Control in Transportation Systems, Tokyo, Japan, 2003; 10th IFAC Symposium on Control in Transportation Systems 2003 ; Conference date: 04-08-2003 Through 06-08-2003",

year = "2003",

doi = "10.1016/S1474-6670(17)32431-X",

language = "English",

volume = "36",

pages = "269--273",

journal = "IFAC Proceedings Volumes (IFAC-PapersOnline)",

issn = "1474-6670",

number = "14",

}

TY - JOUR

T1 - A hybrid model for forecasting local traffic parameters

AU - Belzner, Heidrun

AU - Bogenberger, Klaus

AU - Kates, Ronald

PY - 2003

Y1 - 2003

N2 - Predicting traffic is certainly one of the greatest challenges facing current traffic engineering research. The work presented here focuses on the prediction of local traffic parameters such as the local mean speed aggregated over short periods such as one minute. For this purpose a new hybrid model comprising an ARIMA1 model and a neural network has been developed and validated with real traffic data. This model has been evaluated and compared with conventional methods of traffic prediction using independent real test data. It was found that the new hybrid model produces more accurate and more reliable results than conventional methods.

AB - Predicting traffic is certainly one of the greatest challenges facing current traffic engineering research. The work presented here focuses on the prediction of local traffic parameters such as the local mean speed aggregated over short periods such as one minute. For this purpose a new hybrid model comprising an ARIMA1 model and a neural network has been developed and validated with real traffic data. This model has been evaluated and compared with conventional methods of traffic prediction using independent real test data. It was found that the new hybrid model produces more accurate and more reliable results than conventional methods.

KW - ARIMA models

KW - Backpropagation algorithms

KW - Forecasts

KW - Neural networks

KW - Stochastic realization

UR - http://www.scopus.com/inward/record.url?scp=85064453836&partnerID=8YFLogxK

U2 - 10.1016/S1474-6670(17)32431-X

DO - 10.1016/S1474-6670(17)32431-X

M3 - Conference article

AN - SCOPUS:85064453836

SN - 1474-6670

VL - 36

SP - 269

EP - 273

JO - IFAC Proceedings Volumes (IFAC-PapersOnline)

JF - IFAC Proceedings Volumes (IFAC-PapersOnline)

IS - 14

T2 - 10th IFAC Symposium on Control in Transportation Systems 2003

Y2 - 4 August 2003 through 6 August 2003

ER -

A hybrid model for forecasting local traffic parameters

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this