Exploring the Potential of Neural Networks for Bicycle Travel Time Estimation

Giulia Reggiani; Azita Dabiri; Winnie Daamen; Serge P. Hoogendoorn

doi:10.1007/978-3-030-55973-1_60

Exploring the Potential of Neural Networks for Bicycle Travel Time Estimation

Giulia Reggiani^*, Azita Dabiri, Winnie Daamen, Serge P. Hoogendoorn

^*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

6 Downloads (Pure)

Abstract

A tool for travel time estimation of cyclists approaching a traffic light can monitor level of service of intersections in bike crowded cities. This work represents a first step in developing such a tool. Neural Network models are evaluated on how they perform in estimating individual travel time of cyclists approaching a signalized intersection. Based on simulated scenarios, in cities with low bicycle levels (deterministic scenario), Neural Networks are good travel time estimators whereas, in places with high bike volumes (where cyclists depart with a discharge rate) information on queued cyclists is crucial for travel time information.

Original language	English
Title of host publication	Traffic and Granular Flow 2019
Editors	Iker Zuriguel, Angel Garcimartín, Raúl Cruz Hidalgo
Publisher	Springer Science+Business Media
Pages	487-493
Number of pages	7
ISBN (Print)	9783030559724
DOIs	https://doi.org/10.1007/978-3-030-55973-1_60
Publication status	Published - 2020
Event	13th Conference on Traffic and Granular Flow, TGF 2019 - Pamplona, Spain Duration: 2 Jul 2019 → 5 Jul 2019

Publication series

Name	Springer Proceedings in Physics
Volume	252
ISSN (Print)	0930-8989
ISSN (Electronic)	1867-4941

Conference

Conference	13th Conference on Traffic and Granular Flow, TGF 2019
Country/Territory	Spain
City	Pamplona
Period	2/07/19 → 5/07/19

Bibliographical note

Accepted Author Manuscript

Keywords

Bike travel time estimation
Neural networks
Signalized intersections

Access to Document

10.1007/978-3-030-55973-1_60

Paper 046Accepted author manuscript, 1.25 MB

Cite this

Reggiani, G., Dabiri, A., Daamen, W., & Hoogendoorn, S. P. (2020). Exploring the Potential of Neural Networks for Bicycle Travel Time Estimation. In I. Zuriguel, A. Garcimartín, & R. C. Hidalgo (Eds.), Traffic and Granular Flow 2019 (pp. 487-493). (Springer Proceedings in Physics; Vol. 252). Springer Science+Business Media. https://doi.org/10.1007/978-3-030-55973-1_60

@inproceedings{deb86fee6fe1423bad1b5361a2ecc886,

title = "Exploring the Potential of Neural Networks for Bicycle Travel Time Estimation",

abstract = "A tool for travel time estimation of cyclists approaching a traffic light can monitor level of service of intersections in bike crowded cities. This work represents a first step in developing such a tool. Neural Network models are evaluated on how they perform in estimating individual travel time of cyclists approaching a signalized intersection. Based on simulated scenarios, in cities with low bicycle levels (deterministic scenario), Neural Networks are good travel time estimators whereas, in places with high bike volumes (where cyclists depart with a discharge rate) information on queued cyclists is crucial for travel time information.",

keywords = "Bike travel time estimation, Neural networks, Signalized intersections",

author = "Giulia Reggiani and Azita Dabiri and Winnie Daamen and Hoogendoorn, {Serge P.}",

note = "Accepted Author Manuscript; 13th Conference on Traffic and Granular Flow, TGF 2019 ; Conference date: 02-07-2019 Through 05-07-2019",

year = "2020",

doi = "10.1007/978-3-030-55973-1_60",

language = "English",

isbn = "9783030559724",

series = "Springer Proceedings in Physics",

publisher = "Springer Science+Business Media",

pages = "487--493",

editor = "Iker Zuriguel and Angel Garcimart{\'i}n and Hidalgo, {Ra{\'u}l Cruz}",

booktitle = "Traffic and Granular Flow 2019",

}

Reggiani, G , Dabiri, A , Daamen, W & Hoogendoorn, SP 2020, Exploring the Potential of Neural Networks for Bicycle Travel Time Estimation. in I Zuriguel, A Garcimartín & RC Hidalgo (eds), Traffic and Granular Flow 2019. Springer Proceedings in Physics, vol. 252, Springer Science+Business Media, pp. 487-493, 13th Conference on Traffic and Granular Flow, TGF 2019, Pamplona, Spain, 2/07/19. https://doi.org/10.1007/978-3-030-55973-1_60

Exploring the Potential of Neural Networks for Bicycle Travel Time Estimation. / Reggiani, Giulia ; Dabiri, Azita ; Daamen, Winnie ; Hoogendoorn, Serge P.

Traffic and Granular Flow 2019. ed. / Iker Zuriguel; Angel Garcimartín; Raúl Cruz Hidalgo. Springer Science+Business Media, 2020. p. 487-493 (Springer Proceedings in Physics; Vol. 252).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Exploring the Potential of Neural Networks for Bicycle Travel Time Estimation

AU - Reggiani, Giulia

AU - Dabiri, Azita

AU - Daamen, Winnie

AU - Hoogendoorn, Serge P.

N1 - Accepted Author Manuscript

PY - 2020

Y1 - 2020

N2 - A tool for travel time estimation of cyclists approaching a traffic light can monitor level of service of intersections in bike crowded cities. This work represents a first step in developing such a tool. Neural Network models are evaluated on how they perform in estimating individual travel time of cyclists approaching a signalized intersection. Based on simulated scenarios, in cities with low bicycle levels (deterministic scenario), Neural Networks are good travel time estimators whereas, in places with high bike volumes (where cyclists depart with a discharge rate) information on queued cyclists is crucial for travel time information.

AB - A tool for travel time estimation of cyclists approaching a traffic light can monitor level of service of intersections in bike crowded cities. This work represents a first step in developing such a tool. Neural Network models are evaluated on how they perform in estimating individual travel time of cyclists approaching a signalized intersection. Based on simulated scenarios, in cities with low bicycle levels (deterministic scenario), Neural Networks are good travel time estimators whereas, in places with high bike volumes (where cyclists depart with a discharge rate) information on queued cyclists is crucial for travel time information.

KW - Bike travel time estimation

KW - Neural networks

KW - Signalized intersections

UR - http://www.scopus.com/inward/record.url?scp=85097292459&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-55973-1_60

DO - 10.1007/978-3-030-55973-1_60

M3 - Conference contribution

AN - SCOPUS:85097292459

SN - 9783030559724

T3 - Springer Proceedings in Physics

SP - 487

EP - 493

BT - Traffic and Granular Flow 2019

A2 - Zuriguel, Iker

A2 - Garcimartín, Angel

A2 - Hidalgo, Raúl Cruz

PB - Springer Science+Business Media

T2 - 13th Conference on Traffic and Granular Flow, TGF 2019

Y2 - 2 July 2019 through 5 July 2019

ER -

Exploring the Potential of Neural Networks for Bicycle Travel Time Estimation

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this