Analysis of Spatial Distribution of China's station-free bike-sharing by Clustering Algorithms

Recently, the unbalanced spatial distribution and low utilization rate of the sharing bicycles have caused a serious impact on urban traffic. This study aims to use four clustering algorithms, including k-means clustering algorithm (KM), ant colony clustering algorithm (ACO), fuzzy c-means clustering algorithm (FCM) and mean shift clustering algorithm (MS), to analyze the data of five different density gradients. By analyzing the relationship between the density of bicycle distribution and geographical location, we can get the characteristics of the spatial distribution of shared traffic resources. In this paper, Experimental results have compared the performance of the four clustering algorithms and obtained the best algorithm for the spatial data of China's station-free bike-sharing system.

[1]  Jing Ying,et al.  Station Segmentation with an Improved K-Means Algorithm for Hangzhou Public Bicycle System , 2013, J. Softw..

[2]  Daniel T. Larose,et al.  Discovering Knowledge in Data: An Introduction to Data Mining , 2005 .

[3]  Hui Xiong,et al.  Understanding of Internal Clustering Validation Measures , 2010, 2010 IEEE International Conference on Data Mining.

[4]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[5]  Dirk C. Mattfeld,et al.  Understanding Bike-Sharing Systems using Data Mining: Exploring Activity Patterns , 2011 .

[6]  Larry D. Hostetler,et al.  The estimation of the gradient of a density function, with applications in pattern recognition , 1975, IEEE Trans. Inf. Theory.

[7]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[8]  Marc Zolghadri,et al.  Analysis of bike sharing system by clustering: the Vélib’ case , 2017 .

[9]  Marco Dorigo,et al.  Ant system: optimization by a colony of cooperating agents , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[10]  Vipin Kumar,et al.  Introduction to Data Mining, (First Edition) , 2005 .

[11]  Andrea Rau,et al.  Clustering transformed compositional data using K-means, with applications in gene expression and bicycle sharing system data , 2017, 1704.06150.

[12]  Xifen Xu,et al.  Dockless Bike-Sharing Reallocation Based on Data Analysis: Solving Complex Problem with Simple Method , 2018, 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC).

[13]  Zihan Hong,et al.  Hybrid cluster-regression approach to model bikeshare station usage , 2017, Transportation Research Part A: Policy and Practice.

[14]  Haitao Wang,et al.  Study on Clustering Algorithms of Wireless Self-Organized Network , 2012 .

[15]  Jonathan Corcoran,et al.  Vehicle scheduling approach and its practice to optimise public bicycle redistribution in Hangzhou , 2018, IET Intelligent Transport Systems.

[16]  Gyu M. Lee,et al.  Moment-based rental prediction for bicycle-sharing transportation systems using a hybrid genetic algorithm and machine learning , 2019, Comput. Ind. Eng..