Analyzing Shared Bike Usage Through Graph-Based Spatio-Temporal Modeling
Bike sharing schemes can be used both to improve mobility around busy city routes but also to contribute to the fight against climate change. Optimization of the network in terms of station locations and routes is a focus for researchers, where usage can highlight the precise times at which bike ava...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Intelligent Transportation Systems |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10382155/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590335181586432 |
|---|---|
| author | Dinh Viet Cuong Vuong M. Ngo Paolo Cappellari Mark Roantree |
| author_facet | Dinh Viet Cuong Vuong M. Ngo Paolo Cappellari Mark Roantree |
| author_sort | Dinh Viet Cuong |
| collection | DOAJ |
| description | Bike sharing schemes can be used both to improve mobility around busy city routes but also to contribute to the fight against climate change. Optimization of the network in terms of station locations and routes is a focus for researchers, where usage can highlight the precise times at which bike availability is high in some areas and low in others. Locations for new stations are important for the expansion of the network, but spatio-temporal pattern analysis is required to accurately identify those locations. In other words, one cannot rely on spatial information nor temporal information in isolation, when making interpretations for the purpose of optimizing or expanding the network. In this research, a solution based on graph networks was developed to model activity in transport networks by exploiting properties and functions specific to graph databases. This generic approach adopts a broad series of analyses, comprising different levels of granularity and complexity, to enable better interpretation of network dynamics at a suitably granular level to help the optimization of transport networks. A large dataset provided by an electric bike company is used to address key research questions in both interpreting activity patterns and supporting network optimization. |
| format | Article |
| id | doaj-art-737e8ae8afa34af8bd7d6f67a69ffb2c |
| institution | Kabale University |
| issn | 2687-7813 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Intelligent Transportation Systems |
| spelling | doaj-art-737e8ae8afa34af8bd7d6f67a69ffb2c2025-01-24T00:02:36ZengIEEEIEEE Open Journal of Intelligent Transportation Systems2687-78132024-01-01511513110.1109/OJITS.2024.335021310382155Analyzing Shared Bike Usage Through Graph-Based Spatio-Temporal ModelingDinh Viet Cuong0Vuong M. Ngo1https://orcid.org/0000-0002-8793-0504Paolo Cappellari2Mark Roantree3Insight Centre for Data Analytics, School of Computing, Dublin City University, Dublin 9, IrelandInsight Centre for Data Analytics, School of Computing, Dublin City University, Dublin 9, IrelandCity University of New York, College of Staten Island, Staten Island, NY, USAInsight Centre for Data Analytics, School of Computing, Dublin City University, Dublin 9, IrelandBike sharing schemes can be used both to improve mobility around busy city routes but also to contribute to the fight against climate change. Optimization of the network in terms of station locations and routes is a focus for researchers, where usage can highlight the precise times at which bike availability is high in some areas and low in others. Locations for new stations are important for the expansion of the network, but spatio-temporal pattern analysis is required to accurately identify those locations. In other words, one cannot rely on spatial information nor temporal information in isolation, when making interpretations for the purpose of optimizing or expanding the network. In this research, a solution based on graph networks was developed to model activity in transport networks by exploiting properties and functions specific to graph databases. This generic approach adopts a broad series of analyses, comprising different levels of granularity and complexity, to enable better interpretation of network dynamics at a suitably granular level to help the optimization of transport networks. A large dataset provided by an electric bike company is used to address key research questions in both interpreting activity patterns and supporting network optimization.https://ieeexplore.ieee.org/document/10382155/Spatio-temporal graph analysissmart citytransport networks |
| spellingShingle | Dinh Viet Cuong Vuong M. Ngo Paolo Cappellari Mark Roantree Analyzing Shared Bike Usage Through Graph-Based Spatio-Temporal Modeling IEEE Open Journal of Intelligent Transportation Systems Spatio-temporal graph analysis smart city transport networks |
| title | Analyzing Shared Bike Usage Through Graph-Based Spatio-Temporal Modeling |
| title_full | Analyzing Shared Bike Usage Through Graph-Based Spatio-Temporal Modeling |
| title_fullStr | Analyzing Shared Bike Usage Through Graph-Based Spatio-Temporal Modeling |
| title_full_unstemmed | Analyzing Shared Bike Usage Through Graph-Based Spatio-Temporal Modeling |
| title_short | Analyzing Shared Bike Usage Through Graph-Based Spatio-Temporal Modeling |
| title_sort | analyzing shared bike usage through graph based spatio temporal modeling |
| topic | Spatio-temporal graph analysis smart city transport networks |
| url | https://ieeexplore.ieee.org/document/10382155/ |
| work_keys_str_mv | AT dinhvietcuong analyzingsharedbikeusagethroughgraphbasedspatiotemporalmodeling AT vuongmngo analyzingsharedbikeusagethroughgraphbasedspatiotemporalmodeling AT paolocappellari analyzingsharedbikeusagethroughgraphbasedspatiotemporalmodeling AT markroantree analyzingsharedbikeusagethroughgraphbasedspatiotemporalmodeling |