Advertisement

Discovering Mobility Functional Areas: A Mobility Data Analysis Approach

  • Lorenzo Gabrielli
  • Daniele Fadda
  • Giulio Rossetti
  • Mirco Nanni
  • Leonardo Piccinini
  • Dino Pedreschi
  • Fosca Giannotti
  • Patrizia Lattarulo
Conference paper
Part of the Springer Proceedings in Complexity book series (SPCOM)

Abstract

How do we measure the borders of urban areas and therefore decide which are the functional units of the territory? Nowadays, we typically do that just looking at census data, while in this work we aim to identify functional areas for mobility in a completely data-driven way. Our solution makes use of human mobility data (vehicle trajectories) and consists in an agglomerative process which gradually groups together those municipalities that maximize internal vehicular traffic while minimizing external one. The approach is tested against a dataset of trips involving individuals of an Italian Region, obtaining a new territorial division which allows us to identify mobility attractors. Leveraging such partitioning and external knowledge, we show that our method outperforms the state-of-the-art algorithms. Indeed, the outcome of our approach is of great value to public administrations for creating synergies within the aggregations of the territories obtained.

Notes

Acknowledgements

This work is partially supported by the European Community’s H2020 Program under the scheme ‘INFRAIA-1-2014-2015: Research Infrastructures,’ grant agreement #654024 ‘SoBigData: Social Mining and Big Data Ecosystem’.

References

  1. 1.
    Brezzi, M.: Redefining “Urban”: A New Way to Measure Metropolitan Areas. OECD (2012)Google Scholar
  2. 2.
    ISTAT: Local labour systemGoogle Scholar
  3. 3.
    Boix, R., Veneri, P., Almenar, V.: Polycentric metropolitan areas in europe: towards a unified proposal of delimitation. Defining the Spatial Scale in Modern Regional Analysis, pp. 45–70. Springer, Berlin (2012)Google Scholar
  4. 4.
    Rinzivillo, S., Mainardi, S., Pezzoni, F., Coscia, M., Pedreschi, D., Giannotti, F.: Discovering the geographical borders of human mobility. KI - Künstliche Intell. 26(3), 253–260 (2012)CrossRefGoogle Scholar
  5. 5.
    Fortunato, S.: Community detection in graphs. Phys. Rep. 486(3–5), 75–174 (2010)ADSMathSciNetCrossRefGoogle Scholar
  6. 6.
    Trasarti, R., Rinzivillo, S., Pinelli, F., Nanni, M., Monreale, A., Renso, C., Pedreschi, D., Giannotti, F.: Exploring real mobility data with m-atlas. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 624–627. Springer, Berlin, Heidelberg (2010)Google Scholar
  7. 7.
    Blondel, V.D., Guillaume, J.L., Lambiotte, R., Lefebvre, E.: Fast unfolding of communities in large networks. J. Stat. Mech. Theory Exp. 2008(10), P10008 (2008)CrossRefGoogle Scholar
  8. 8.
    Fortunato, S., Barthélemy, M.: Resolution limit in community detection. PNAS 104(1), 36–41 (2007)ADSCrossRefGoogle Scholar
  9. 9.
    Coscia, M., Rossetti, G., Giannotti, F., Pedreschi, D.: Demon: a local-first discovery method for overlapping communities. In: Agarwal, D., Pei, J. (eds.) KDD, Q.Y. 0001, pp. 615–623. ACM (2012)Google Scholar
  10. 10.
    Rosvall, M., Bergstrom, C.T.: Maps of random walks on complex networks reveal community structure. Proc. Natl. Acad. Sci. 105(4), 1118–1123 (2008)ADSCrossRefGoogle Scholar
  11. 11.
    Rousseeuw, P.J.: Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. 20, 53–65 (1987)CrossRefMATHGoogle Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Lorenzo Gabrielli
    • 1
  • Daniele Fadda
    • 1
  • Giulio Rossetti
    • 1
    • 2
  • Mirco Nanni
    • 1
  • Leonardo Piccinini
    • 3
  • Dino Pedreschi
    • 2
  • Fosca Giannotti
    • 1
  • Patrizia Lattarulo
    • 3
  1. 1.KDD Lab. ISTI-CNR1 PisaItaly
  2. 2.University of Pisa2 PisaItaly
  3. 3.IRPETFirenzeItaly

Personalised recommendations