Abstract
Microsimulation of travel flows aims to assess the effect of decisions taken by travelers based on personal preferences, time-of-day, properties of the infrastructure and expected or perceived travel flows. Route choice represents a particular class of such decisions. Route choice prediction is an essential component of microsimulators. Specification of choice models and estimation of the corresponding parameters based on observations are required in the preparatory stage. Route choice sets need to be established for sampling in the simulation stage. This paper is part of a research project aiming to investigate how route complexity can be integrated in the choice process modeling. In particular routes for bikers collected by GPS tracking in the Dutch FietsTelWeek project in 2016 are analyzed. The data exploration stage and the research project outline are covered. Properties of the publicly available fietstelweek2016 dataset used for model training are investigated in order to assess their effect on prediction results. In order to achieve the project goal, the research project structure is briefly discussed. It is based on the observation that the number of routes recorded for each OD-pair is too small to observe a frequency distribution for complexity. Hence, complexity data are collected for sub-networks that are similar with respect to particular graph properties.
| Original language | English |
|---|---|
| Pages (from-to) | 401-408 |
| Number of pages | 8 |
| Journal | Procedia Computer Science |
| Volume | 151 |
| Early online date | 21 May 2019 |
| DOIs | |
| Publication status | Published - 2019 |
| Event | 10th International Conference on Ambient Systems, Networks and Technologies, ANT 2019 and The 2nd International Conference on Emerging Data and Industry 4.0, EDI40 2019, Affiliated Workshops - Leuven, Belgium Duration: 29 Apr 2019 → 2 May 2019 |
Fingerprint
Bibliographical note
Part of special issue: The 10th International Conference on Ambient Systems, Networks and Technologies (ANT 2019) / The 2nd International Conference on Emerging Data and Industry 4.0 (EDI40 2019) / Affiliated Workshops. Edited by Elhadi ShakshukiKeywords
- Bicycle
- Choice set
- GPS traces
- Route
Cite this
}
Bicyclist route choice : Data exploration and research project outline. / Knapen, Luk; Koch, Thomas; Dugundji, Elenna.
In: Procedia Computer Science, Vol. 151, 2019, p. 401-408.Research output: Contribution to Journal › Article › Academic › peer-review
TY - JOUR
T1 - Bicyclist route choice
T2 - Data exploration and research project outline
AU - Knapen, Luk
AU - Koch, Thomas
AU - Dugundji, Elenna
N1 - Part of special issue: The 10th International Conference on Ambient Systems, Networks and Technologies (ANT 2019) / The 2nd International Conference on Emerging Data and Industry 4.0 (EDI40 2019) / Affiliated Workshops. Edited by Elhadi Shakshuki
PY - 2019
Y1 - 2019
N2 - Microsimulation of travel flows aims to assess the effect of decisions taken by travelers based on personal preferences, time-of-day, properties of the infrastructure and expected or perceived travel flows. Route choice represents a particular class of such decisions. Route choice prediction is an essential component of microsimulators. Specification of choice models and estimation of the corresponding parameters based on observations are required in the preparatory stage. Route choice sets need to be established for sampling in the simulation stage. This paper is part of a research project aiming to investigate how route complexity can be integrated in the choice process modeling. In particular routes for bikers collected by GPS tracking in the Dutch FietsTelWeek project in 2016 are analyzed. The data exploration stage and the research project outline are covered. Properties of the publicly available fietstelweek2016 dataset used for model training are investigated in order to assess their effect on prediction results. In order to achieve the project goal, the research project structure is briefly discussed. It is based on the observation that the number of routes recorded for each OD-pair is too small to observe a frequency distribution for complexity. Hence, complexity data are collected for sub-networks that are similar with respect to particular graph properties.
AB - Microsimulation of travel flows aims to assess the effect of decisions taken by travelers based on personal preferences, time-of-day, properties of the infrastructure and expected or perceived travel flows. Route choice represents a particular class of such decisions. Route choice prediction is an essential component of microsimulators. Specification of choice models and estimation of the corresponding parameters based on observations are required in the preparatory stage. Route choice sets need to be established for sampling in the simulation stage. This paper is part of a research project aiming to investigate how route complexity can be integrated in the choice process modeling. In particular routes for bikers collected by GPS tracking in the Dutch FietsTelWeek project in 2016 are analyzed. The data exploration stage and the research project outline are covered. Properties of the publicly available fietstelweek2016 dataset used for model training are investigated in order to assess their effect on prediction results. In order to achieve the project goal, the research project structure is briefly discussed. It is based on the observation that the number of routes recorded for each OD-pair is too small to observe a frequency distribution for complexity. Hence, complexity data are collected for sub-networks that are similar with respect to particular graph properties.
KW - Bicycle
KW - Choice set
KW - GPS traces
KW - Route
UR - http://www.scopus.com/inward/record.url?scp=85071935073&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85071935073&partnerID=8YFLogxK
U2 - 10.1016/j.procs.2019.04.055
DO - 10.1016/j.procs.2019.04.055
M3 - Article
VL - 151
SP - 401
EP - 408
JO - Procedia Computer Science
JF - Procedia Computer Science
SN - 1877-0509
ER -