標題: 台北公共自行車租賃系統使用型態之分析
Better understanding the Taipei public bikesharing system: Exploring activity patterns
作者: 鄭群彥
Cheng, Chun-Yen
汪進財
Wong, Jinn-Tsai
運輸與物流管理學系
關鍵字: 公共自行車租賃系統、使用型態、資料探勘、集群分析;public bikesharing system, station activity pattern, data mining, cluster analysis
公開日期: 2013
摘要: City-wide urban infrastructure are increasing reliant on information and communication technology (ICT) to improve and expand the service. Therefore, by taking advantage of passive sensors and Open Data policy, large scale of human behaviour data can be sensed and become more easily accessed independently. Data mining plays a vital role in helping to discover the patterns of human behaviour. In this study, we focus on the emerging urban transport infrastructure: public bikesharing system of Taipei City: YouBike. YouBike is launched from August 2012, operated by Giant, recognised as the world’s largest bicycle manufacturer. Besides, it was the first large-scale public bike sharing system to be implemented in Taiwan. Currently, there are 166 bike station is operation. This study has shown that how bikesharing usage data which mainly focuses on the changes of the number of available bicycles across all stations not only reveals the station activity patterns but also explores the underlying temporal and spatial dynamics of a city. The clustering results indicate that station activity patterns could be categorised into three groups: which are daytime origins nighttime destinations, daytime destinations nighttime origins, and combined origins and destinations. Each cluster groups reveal the different activity patterns throughout the day. We believe that the visualisation of average temporal activity patterns and the clustered results could easily lead to a better understanding of the bicycle availability information. In addition, it is expected to improve the Taipei YouBike service itself, avoiding a future empty or full station through an improved redistribution of bicycles via rebalancing trucks. As a result, it would help to improve user satisfaction with the enhanced service and it is possible to attract more people to use YouBike as an enhanced green transport system.
City-wide urban infrastructure are increasing reliant on information and communication technology (ICT) to improve and expand the service. Therefore, by taking advantage of passive sensors and Open Data policy, large scale of human behaviour data can be sensed and become more easily accessed independently. Data mining plays a vital role in helping to discover the patterns of human behaviour. In this study, we focus on the emerging urban transport infrastructure: public bikesharing system of Taipei City: YouBike. YouBike is launched from August 2012, operated by Giant, recognised as the world’s largest bicycle manufacturer. Besides, it was the first large-scale public bike sharing system to be implemented in Taiwan. Currently, there are 166 bike station is operation. This study has shown that how bikesharing usage data which mainly focuses on the changes of the number of available bicycles across all stations not only reveals the station activity patterns but also explores the underlying temporal and spatial dynamics of a city. The clustering results indicate that station activity patterns could be categorised into three groups: which are daytime origins nighttime destinations, daytime destinations nighttime origins, and combined origins and destinations. Each cluster groups reveal the different activity patterns throughout the day. We believe that the visualisation of average temporal activity patterns and the clustered results could easily lead to a better understanding of the bicycle availability information. In addition, it is expected to improve the Taipei YouBike service itself, avoiding a future empty or full station through an improved redistribution of bicycles via rebalancing trucks. As a result, it would help to improve user satisfaction with the enhanced service and it is possible to attract more people to use YouBike as an enhanced green transport system.
URI: http://140.113.39.130/cdrfb3/record/nctu/#GT070053603
http://hdl.handle.net/11536/75462
Appears in Collections:Thesis


Files in This Item:

  1. 360301.pdf