Clustering-based methodology for estimating bicycle accumulation levels on signalized links
A case study from the Netherlands
G. Reggiani (TU Delft - Transport and Planning)
Azita Dabiri (TU Delft - Transport and Planning, TU Delft - Team Bart De Schutter)
W Daamen (TU Delft - Transport and Planning)
Serge Hoogendoorn (TU Delft - Transport and Planning)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
The number of queued bicycles on a signalised link is crucial information for the adoption of intelligent transport systems, aiming at a better management of cyclists in cities. An unsupervised machine learning methodology is deployed to produce estimations of accumulation levels based on data retrieved from a bicycle street of the Netherlands. The use of a clustering-based approach, combined with a conceptual insight into the bicycle accumulation process and various data sources, makes the applied methodology less dependent on sensor errors. This clustering-based methodology is a first step in bicycle accumulation estimation and clearly identifies levels of cyclists accumulated in front of a traffic light.