Clustering-based methodology for estimating bicycle accumulation levels on signalized links
Autor: | Azita Dabiri, Serge P. Hoogendoorn, Winnie Daamen, Giulia Reggiani |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2019 |
Předmět: |
Off-line and Online Data Processing Techniques
050210 logistics & transportation Computer science 05 social sciences Process (computing) Modeling 010501 environmental sciences computer.software_genre 01 natural sciences Data Mining and Data Analysis and Control of Pedestrians and Cyclists 0502 economics and business Unsupervised learning Modeling Simulation and Control of Pedestrians and Cyclists Data mining Cluster analysis Intelligent transportation system computer Simulation 0105 earth and related environmental sciences |
Zdroj: | 2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019 ITSC |
DOI: | 10.1109/itsc.2019.8917138 |
Popis: | 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. |
Databáze: | OpenAIRE |
Externí odkaz: |