Abstract
With the popularity of bike-sharing system in cities, a large volume of bike-sharing data, which contain the spatio-temporal characteristics of riders, are generated. These data enable a number of important location-aware services such as detecting hot-spots and predicting traffic in a city. This paper develops a system for Mining and Analysing Hot-Spots (MAHS) from bike-sharing data which are collected from Beijing within a week. Firstly, according to different time granularity and space distance, MAHS visually figures the spatio-temporal statistical information of bike-sharing data by graph. Secondly, utilizing POI data from Amap API and the density peak clustering algorithm, MAHS discoveries hot-spots on start-locations and end-locations during the morning and evening rush hours, and intuitively illustrates them on map. Thirdly, based on the LDA algorithm, MAHS identifies the city functions of hot-spots and the moving patterns of riders, and concisely demonstrates them on map. MAHS can help users with managing bike-sharing system, understanding the moving patterns of riders, finding the functional regions of cities, and other urban computing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Midgley, P.: The role of smart bike-sharing systems in urban mobility. Journeys 2(1), 23–31 (2009)
Lu, M., Liang, J., Wang, Z., et al.: Exploring OD patterns of interested region based on taxi trajectories. J. Vis. 19(4), 811–821 (2016)
Xu, X., Zhou, J., Liu, Y., et al.: Taxi-RS: taxi-hunting recommendation system based on taxi GPS data. IEEE Trans. Intell. Transp. Syst. 16(4), 1716–1727 (2015)
Rodriguez, A., Laio, A.: Clustering by fast search and find of density peaks. Science 344(6191), 1492–1496 (2014)
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)
China association of artificial intelligence: 2017 mobike cup algorithm challenge. https://biendata.com/competition/mobike/. (June 2017)
Acknowledgment
This work is supported by the National Natural Science Foundation of China (61662086, 61762090, 61966036), and the Project of Innovation Research Team of Yunnan Province (2018HC019).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, Y., Ma, D., Chen, H., Zhou, L. (2021). MAHS: A System for Mining and Analysing Hot-Spots from Bike-Sharing Data. In: Meng, H., Lei, T., Li, M., Li, K., Xiong, N., Wang, L. (eds) Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery. ICNC-FSKD 2020. Lecture Notes on Data Engineering and Communications Technologies, vol 88. Springer, Cham. https://doi.org/10.1007/978-3-030-70665-4_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-70665-4_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-70664-7
Online ISBN: 978-3-030-70665-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)