A Data-Driven Approach for Travel Time Prediction on Motorway Sections

Bernhard Heilmann; Hannes Koller; Johannes Asamer; Martin Reinthaler; Michael Aleksa; Simon Breuss; Gerald Richter

doi:10.1109/ICCVE.2014.7297598

A Data-Driven Approach for Travel Time Prediction on Motorway Sections

Bernhard Heilmann
, Hannes Koller
, Johannes Asamer
, Martin Reinthaler (Speaker)
, Michael Aleksa
, Simon Breuss
, Gerald Richter

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation › peer-review

Abstract

In the presented case study, travel times for passenger cars (PC) and heavy goods vehicles (HGV) were predicted with a data-driven, hybrid approach, using historical traffic data of the entire high-ranking Austrian road network. In case flow data were available, travel time was predicted with a Kernel predictor searching for similar speed-density patterns. In case of missing flow data, travel time was predicted with deviations from typical historical speed time series. The performed steps in pre-processing traffic data, the hybrid prediction method as well as the results for selected road sections are described and analysed.

Original language	English
Title of host publication	Proceedings 2014 International Conference on Connected Vehicles and Expo (ICCVE2014)
DOIs	https://doi.org/10.1109/ICCVE.2014.7297598
Publication status	Published - 2014
Event	2014 International Conference on Connected Vehicles and Expo (ICCVE 2014) - Duration: 3 Jul 2014 → 7 Nov 2014

Conference

Conference	2014 International Conference on Connected Vehicles and Expo (ICCVE 2014)
Period	3/07/14 → 7/11/14

Research Field

Former Research Field - Mobility Systems

Access to Document

10.1109/ICCVE.2014.7297598Licence: Unspecified

Cite this

@inproceedings{204062807b9348bb934717efa31510d5,

title = "A Data-Driven Approach for Travel Time Prediction on Motorway Sections",

abstract = "In the presented case study, travel times for passenger cars (PC) and heavy goods vehicles (HGV) were predicted with a data-driven, hybrid approach, using historical traffic data of the entire high-ranking Austrian road network. In case flow data were available, travel time was predicted with a Kernel predictor searching for similar speed-density patterns. In case of missing flow data, travel time was predicted with deviations from typical historical speed time series. The performed steps in pre-processing traffic data, the hybrid prediction method as well as the results for selected road sections are described and analysed.",

author = "Bernhard Heilmann and Hannes Koller and Johannes Asamer and Martin Reinthaler and Michael Aleksa and Simon Breuss and Gerald Richter",

year = "2014",

doi = "10.1109/ICCVE.2014.7297598",

language = "English",

booktitle = "Proceedings 2014 International Conference on Connected Vehicles and Expo (ICCVE2014)",

note = "2014 International Conference on Connected Vehicles and Expo (ICCVE 2014) ; Conference date: 03-07-2014 Through 07-11-2014",

}

Heilmann, B , Koller, H, Asamer, J, Reinthaler, M, Aleksa, M, Breuss, S & Richter, G 2014, A Data-Driven Approach for Travel Time Prediction on Motorway Sections. in Proceedings 2014 International Conference on Connected Vehicles and Expo (ICCVE2014). 2014 International Conference on Connected Vehicles and Expo (ICCVE 2014), 3/07/14. https://doi.org/10.1109/ICCVE.2014.7297598

TY - GEN

T1 - A Data-Driven Approach for Travel Time Prediction on Motorway Sections

AU - Heilmann, Bernhard

AU - Koller, Hannes

AU - Asamer, Johannes

AU - Aleksa, Michael

AU - Breuss, Simon

AU - Richter, Gerald

A2 - Reinthaler, Martin

PY - 2014

Y1 - 2014

N2 - In the presented case study, travel times for passenger cars (PC) and heavy goods vehicles (HGV) were predicted with a data-driven, hybrid approach, using historical traffic data of the entire high-ranking Austrian road network. In case flow data were available, travel time was predicted with a Kernel predictor searching for similar speed-density patterns. In case of missing flow data, travel time was predicted with deviations from typical historical speed time series. The performed steps in pre-processing traffic data, the hybrid prediction method as well as the results for selected road sections are described and analysed.

AB - In the presented case study, travel times for passenger cars (PC) and heavy goods vehicles (HGV) were predicted with a data-driven, hybrid approach, using historical traffic data of the entire high-ranking Austrian road network. In case flow data were available, travel time was predicted with a Kernel predictor searching for similar speed-density patterns. In case of missing flow data, travel time was predicted with deviations from typical historical speed time series. The performed steps in pre-processing traffic data, the hybrid prediction method as well as the results for selected road sections are described and analysed.

U2 - 10.1109/ICCVE.2014.7297598

DO - 10.1109/ICCVE.2014.7297598

M3 - Conference Proceedings with Oral Presentation

BT - Proceedings 2014 International Conference on Connected Vehicles and Expo (ICCVE2014)

T2 - 2014 International Conference on Connected Vehicles and Expo (ICCVE 2014)

Y2 - 3 July 2014 through 7 November 2014

ER -

A Data-Driven Approach for Travel Time Prediction on Motorway Sections

Abstract

Conference

Research Field

Access to Document

Fingerprint

Cite this