A Study on Bicycle-Sharing Dispatching Station Site Selection and Planning Based on Multivariate Data

Bicycle-sharing is experiencing rapidly as a low-carbon transport mode of travel, with the advantages low cost and sustainability. operators use electronic fence parking points to manage bicycle-sharing, but it too time-consuming impractical them individually. Therefore, necessary cluster implement regionalized management. This study uses Mean-shift clustering algorithm on Xiamen Island, construct bicycle-sharing dispatching station, divide management area. Singular value decomposition employed analyze travel demand patterns characteristics. In addition, we constructed regression models explore relationship between urban built environment trips during morning evening peak hours. The results show that: (1) 73 stations cover 86.72% data, good effect. (2) for shows multiple different characteristics in spatial temporal distributions, which are influenced by land use. (3) There differences impact trips, especially residential enterprise poi densities have opposite effects shared research this paper can serve planning dispatch differentiated reduce operating costs promote development sustainable transport.