Predicting Social Density in Mass Events to Prevent Crowd Disasters

  • Bernhard Anzengruber
  • Danilo Pianini
  • Jussi Nieminen
  • Alois Ferscha
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8238)


Human mobility behavior emerging in social events involving huge masses of individuals bears potential hazards for irrational social densities. We study the emergence of such phenomena in the context of very large public sports events, analyzing how individual mobility decision making induces undesirable mass effects. A time series based approach is followed to predict mobility patterns in crowds of spectators, and related to the event agenda over the time it evolves. Evidence is collected from an experiment conducted in one of the biggest international sports events (the Vienna city marathon with 40.000 actives and around 300.000 spectators). A smartphone app has been developed to voluntarily engage people to provide mobility data (1503 high-quality GPS traces and 1092694 Bluetooth relations have been collected), based on which prediction analysis has been performed. Using this data as training set, we compare density estimation approaches and evaluate them based on their forecasting precision. The most promising approach using Support Vector Regression (SMOreg) achieved prediction accuracies below 2 (root-mean-squared deviation) when compared to actual evidenced density distributions for a 12 minute forecasting interval.


Support Vector Machine Support Vector Regression Time Series Forecast Density Pair Absolute Density 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Antonini, G., Bierlaire, M., Weber, M.: Discrete choice models of pedestrian walking behavior. Transportation Research Part B: Methodological 40(8), 667–687 (2006)CrossRefGoogle Scholar
  2. 2.
    Berkelaar, M., Eikland, K., Notebaert, P., et al.: lpsolve: Open source (mixed-integer) linear programming system. Eindhoven U. of Technology (2004)Google Scholar
  3. 3.
    Brown, R.: Smoothing, Forecasting and Prediction of Discrete Time Series, Dover Phoenix Editions. Dover Publications (2004)Google Scholar
  4. 4.
    Burke, J., Estrin, D., Hansen, M., Parker, A., Ramanathan, N., Reddy, S., Srivastava, M.B.: Participatory sensing. In: Workshop on World-Sensor-Web (WSW 2006): Mobile Device Centric Sensor Networks and Applications, pp. 117–134 (2006)Google Scholar
  5. 5.
    Burstedde, C., Klauck, K., Schadschneider, A., Zittartz, J.: Simulation of pedestrian dynamics using a two-dimensional cellular automaton. Physica A: Statistical Mechanics and its Applications 295(3-4), 507–525 (2001)CrossRefzbMATHGoogle Scholar
  6. 6.
    Cortes, C., Vapnik, V.: Support-vector networks. Machine Learning 20(3), 273–297 (1995)zbMATHGoogle Scholar
  7. 7.
    Eagle, N., Pentland, A.: Social serendipity: mobilizing social software. IEEE Pervasive Computing 4(2), 28–34 (2005)CrossRefGoogle Scholar
  8. 8.
    Fruin, J.: The causes and prevention of crowd disasters. In: Smith, R.A., Dickie, J.F. (eds.) Engineering for Crowd Safety, pp. 99–108 (1993)Google Scholar
  9. 9.
    Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: an update. SIGKDD Explor. Newsl. 11(1), 10–18 (2009)CrossRefGoogle Scholar
  10. 10.
    Helbing, D., Buzna, L., Johansson, A., Werner, T.: Self-organized pedestrian crowd dynamics: Experiments, simulations, and design solutions. Transportation Science 39(1), 1–24 (2005)CrossRefGoogle Scholar
  11. 11.
    Helbing, D., Johansson, A.: Pedestrian, Crowd, and Evacuation Dynamics, pp. 6476–6495. Springer, New York (2009)Google Scholar
  12. 12.
    Helbing, D., Mukerji, P.: Crowd disasters as systemic failures: analysis of the love parade disaster. EPJ Data Science 1(1), 7 (2012)CrossRefGoogle Scholar
  13. 13.
    Herrmann, S.: Ivory coast mourns after new year stampede in abidjan (January 2013),
  14. 14.
    Hsu, W.-L., Lin, K.-F., Tsai, C.-L.: Crowd density estimation based on frequency analysis. In: 2011 Seventh International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP), pp. 348–351 (2011)Google Scholar
  15. 15.
    Jetcheva, J., Hu, Y.-C., PalChaudhuri, S., Saha, A., Johnson, D.: Design and evaluation of a metropolitan area multitier wireless ad hoc network architecture. In: Proceedings of the 5th IEEE Workshop on Mobile Computing Systems and Applications, Monterey, CA, USA, pp. 32–43 (October 2003)Google Scholar
  16. 16.
    Klingsch, W., Rogsch, C., Schadschneider, A.: Pedestrian and Evacuation Dynamics 2008. Springer, Heidelberg (2010)CrossRefzbMATHGoogle Scholar
  17. 17.
    Lee, K., Hong, S., Kim, S.J., Rhee, I., Chong, S.: Slaw: A mobility model for human walks. In: Proceedings of the 28th Annual Joint Conference of the IEEE Computer and Communications Societies (INFOCOM), Rio de Janeiro, Brazil. IEEE (April 2009)Google Scholar
  18. 18.
    Ma, R., Li, L., Huang, W., Tian, Q.: On pixel count based crowd density estimation for visual surveillance. In: 2004 IEEE Conference on Cybernetics and Intelligent Systems, vol. 1, pp. 170–173 (2004)Google Scholar
  19. 19.
    Mackay, D.J.: Introduction to gaussian processes (1998)Google Scholar
  20. 20.
    Mäkelä, K., Belt, S., Greenblatt, D., Häkkilä, J.: Mobile interaction with visual and rfid tags: a field study on user perceptions. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, CHI 2007, pp. 991–994. ACM, New York (2007)CrossRefGoogle Scholar
  21. 21.
    Monge, G.: Memoire sur la theorie des delais et des remblais. In: Histoire de lAcademie Royale des Sciences de Paris, avec les Memoires de Mathematique et de Physique pour la meme annee, pp. 666–704 (1781)Google Scholar
  22. 22.
    Nakatsuka, M., Iwatani, H., Katto, J.: A study on passive crowd density estimation using wireless sensors. In: 4th International Conference on Mobile Computing and Ubiquitous Networking (ICMU), Tokyo, Japan (2008)Google Scholar
  23. 23.
    Natarajan, A., Motani, M., Srinivasan, V.: Understanding urban interactions from bluetooth phone contact traces. In: Uhlig, S., Papagiannaki, K., Bonaventure, O. (eds.) PAM 2007. LNCS, vol. 4427, pp. 115–124. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  24. 24.
    Nicholson, C., Roebuck, B.: The investigation of the hillsborough disaster by the health and safety executive. Safety Science 18(4), 249–259 (1995)CrossRefGoogle Scholar
  25. 25.
    Pietilänen, A.-K., Diot, C.: Dissemination in opportunistic social networks: the role of temporal communities. In: Proceedings of the Thirteenth ACM International Symposium on Mobile Ad Hoc Networking and Computing, MobiHoc 2012, pp. 165–174. ACM, New York (2012)CrossRefGoogle Scholar
  26. 26.
    Su, J., Chan, K.K.W., Miklas, A.G., Po, K., Akhavan, A., Saroiu, S., de Lara, E., Goel, A.: A preliminary investigation of worm infections in a bluetooth environment. In: Proceedings of the 4th ACM Workshop on Recurring Malcode, WORM 2006, pp. 9–16. ACM, New York (2006)Google Scholar
  27. 27.
    Weppner, J., Lukowicz, P.: Bluetooth based collaborative crowd density estimation with mobile phones. In: IEEE International Conference on Pervasive Computing and Communications (PerCom), vol. 18, p. 22 (2013)Google Scholar
  28. 28.
    Wirz, M., Franke, T., Roggen, D., Mitleton-Kelly, E., Lukowicz, P., Troster, G.: Inferring crowd conditions from pedestrians’ location traces for real-time crowd monitoring during city-scale mass gatherings. In: 2012 IEEE 21st International Workshop on Enabling Technologies: Infrastructure for Collaborative Enterprises, pp. 367–372 (2012)Google Scholar
  29. 29.
    Wirz, M., Franke, T., Roggen, D., Mitleton-Kelly, E., Lukowicz, P., Trster, G.: Probing crowd density through smartphones in city-scale mass gatherings. In: EPJ Data Science, pp. 1–24 (2013)Google Scholar
  30. 30.
    Zheng, Y., Li, Q., Chen, Y., Xie, X., Ma, W.-Y.: Understanding mobility based on gps data. In: Proceedings of ACM Conference on Ubiquitous Computing (UbiComp 2008), pp. 312–321. ACM Press, Seoul (2008)Google Scholar
  31. 31.
    Zia, K., Riener, A., Ferscha, A., Sharpanskykh, A.: Evacuation simulation based on cognitive decision making model in a socio-technical system. In: IEEE/ACM International Symposium on Distributed Simulation and Real Time Applications, pp. 98–107 (2011)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Bernhard Anzengruber
    • 1
  • Danilo Pianini
    • 2
  • Jussi Nieminen
    • 1
  • Alois Ferscha
    • 1
  1. 1.Institute for Pervasive ComputingJohannes Kepler University LinzAustria
  2. 2.Department of Computer Science and Engineering - DISIAlma Mater Studiorum Università di BolognaItaly

Personalised recommendations