EXTRACTING HIDDEN FEATURES OF HUMAN MOBILITY AND PREDICTING INFLOW AND OUTFLOW OF BIKE SHARING STATIONS

Huge amounts of spatial-temporal data are generated daily from all kinds of citywide infrastructures. Understanding and predicting accurately such a large amount of data could benefit many real world applications. This paper provides an analysis of human mobility data in an urban area using the amount ofavailable bikes in the stations of the bicycle sharing program. Based on data sampled from the operator's website, it is possible to detect temporal and geographic mobility patterns within the city. These patterns are applied to predict the number ofavailable bikes for any station some hours ahead. Our methodology first identifies and quantifies the latent characteristics of different spatial environments and temporal factors through tensor factorization. Our hypothesis is that the patterns of spatial-temporal activities are highly dependent on or caused by these latent spatial-temporal features. We model this hidden dependent relationship as a Gaussian process, which can be viewed as a distribution over the possible functions to predict human mobility.

1. Bike sharing world maps web site. URL: www.bikesharingmap.com

2. Kazakhstani bike sharing systems web sites. URL: https://velobike.kz/, https://almatybike.kz/, https://shymkentbike.kz/

3. Borgnat, P., Robardet, C., Abry, P., Flandrin, P., Rouquier, J.-B., & Tremblay, N. (2013). A dynamical network view of Lyon ' S. V. ' Elo ' v shared bicycle system. Dynamics on and of Complex Networks, 2, 267-284.

4. O’Brien, O., Cheshire, J., & Batty, M. (2014). Mining bicycle sharing data for generating insights into sustainable transport systems. Journal of Transport Geography, 34, 262-273. Retrieved from http://linkinghub.elsevier.com/retrieve/pii/S0966692313001178

5. Zaltz Austwick, M., O’Brien, O., Strano, E., Viana, M., & Gomez-Gardenes, J. (2013). The structure of spatial networks and communities in bicycle sharing systems. PLoS ONE, 8 (9), e74685, 1-17.

6. Goodman, A., & Cheshire, J. (2014). Inequalities in the London bicycle sharing system revisited: Impacts of extending the scheme to poorer areas but then doubling prices. Journal of Transport Geography. Retrieved from http://linkinghub.elsevier.com/retrieve/pii/S0966692314000659

7. Lin, J. H., & Chou, T. C. (2012). A geo-aware and VRP-based public bicycle redistribution system. International Journal of Vehicular Technology, 2012, 1-14.

8. Raviv, T., Tzur, M., & Forma, I. A. (2013). Static repositioning in a bike-sharing system: Models and solution approaches. EURO Journal on Transportation and Logistics, 2 (3), 187-229. Retrieved from http://link.springer.com/10.1007/s13676-012-0017-6

9. Systems, D. T. & Lackner, B. (2013). Modeling demand for bicycle sharing systems - Neighboring stations as a source for demand and a reason for structural breaks. TRB, 1-19.

10. Garcia-Palomares, J. C., Gutierrez, J., & Latorre, M. (2012). Optimizing the location of stations in bike-sharing programs: A GIS approach. Applied Geography, 35 (1-2), 235-246.

11. Romanillos, G., Zaltz Austwick, M., Ettema, D., & De Kruijf, J. (2016). Big data and cycling. Transport Reviews, 36 (1), 114-133.

12. Khatri, R. (2015). Modeling route choice of Utilitarian Bikeshare users from GPS Data. University of Tennessee. Retrieved from http://trace.tennessee.edu/cgi/viewcontent.cgi?article=4837&context=utk_gradthes

13. Wergin, J., & Buehler, R. 2018. Where do bikeshare bikes actually Go? An analysis of capital bikeshare trips using GPS data. Transportation Research Record, (January), 2662, 12-21.

14. Gustavo Romanillos, Borja Moya-Gomez, Martin Zaltz-Austwick & Patxi J. Lamiquiz-Dauden (2018) The pulse of the cycling city: visualising Madrid bike share system GPS routes and cycling flow, Journal of Maps, 14:1, 34-43, DOI: 10.1080/17445647.2018.1438932

15. Kolda, T. G., & Bader, B. W. (2009). Tensor decompositions and applications. SIAM Review, 51, 455-500.

16. Rasmussen, C. E. (2006). “Gaussian processes for machine learning.”