Temporal Analysis of 911 Emergency Calls Through Time Series Modeling

  • Pablo Robles
  • Andrés Tello
  • Lizandro Solano-QuindeEmail author
  • Miguel Zúñiga-Prieto
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1066)


We present two techniques for modeling time series of emergency events using data from 911 emergency calls in the city of Cuenca-Ecuador. We study state-of-the-art methods for time series analysis and assess the benefits and drawbacks of each one of them. In this paper, we develop an emergency model using a large dataset corresponding to the period January 1st 2015 through December 31st 2016 and test a Gaussian Process and an ARIMA model for temporal prediction purposes. We assess the performance of our approaches experimentally, comparing the standard residual error (SRE) and the execution time of both models. In addition, we include climate and holidays data as explanatory variables of the regressions aiming to improve the prediction. The results show that ARIMA model is the most suitable one for forecasting emergency events even without the support of additional variables.


911 calls Emergency calls Temporal models GP ARIMA 



This article is part of the project “Análisis predictivo de la ocurrencia de eventos de emergencia en la provincia del Azuay”, winner of the “XV Concurso Universitario de Proyectos de Investigación” funded by the Dirección de Investigación de la Universidad de Cuenca. The authors also thank the Servicio Integrado de Seguridad ECU911 - Zona 6 for their collaboration and data provided.


  1. 1.
    Ecu 911 website.
  2. 2.
    Bappee, F.K., Júnior, A.S., Matwin, S.: Predicting crime using spatial features. CoRR abs/1803.04474 (2018).
  3. 3.
    Chandrasekar, A., Raj, A.S., Kumar, P.: Crime prediction and classification in San Francisco cityGoogle Scholar
  4. 4.
    Chirigati, F., Doraiswamy, H., Damoulas, T., Freire, J.: Data polygamy: the many-many relationships among urban spatio-temporal data sets. In: Proceedings of the 2016 International Conference on Management of Data, SIGMOD 2016, pp. 1011–1025. ACM, New York(2016).
  5. 5.
    Chohlas-Wood, A., Merali, A., Reed, W.R., Damoulas, T.: Mining 911 calls in New York City: temporal patterns, detection, and forecasting. In: AAAI Workshop: AI for Cities (2015)Google Scholar
  6. 6.
    Cramer, D., Brown, A.A., Hu, G.: Predicting 911 calls using spatial analysis, pp. 15–26. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  7. 7.
    Flaxman, S., Chirico, M., Pereira, P., Loeffler, C.: Scalable high-resolution forecasting of sparse spatiotemporal events with kernel methods: a winning solution to the NIJ “real-time crime forecasting challenge”. arXiv preprint arXiv:1801.02858 (2018)
  8. 8.
    Flaxman, S.R.: A general approach to prediction and forecasting crime rates with Gaussian processes. Carnegie Mellon University, Heinz College Second Paper, Pittsburg (2014)Google Scholar
  9. 9.
    Hilbe, J.M.: Modeling count data. In: International Encyclopedia of Statistical Science, pp. 836–839. Springer (2011)Google Scholar
  10. 10.
    Ihueze, C.C., Onwurah, U.O.: Road traffic accidents prediction modelling: an analysis of Anambra State, Nigeria. Accid. Anal. Prev. 112, 21–29 (2018)CrossRefGoogle Scholar
  11. 11.
    Kim, S.Y., Maciejewski, R., Malik, A., Jang, Y., Ebert, D.S., Isenberg, T.: Bristle maps: a multivariate abstraction technique for geovisualization. IEEE Trans. Vis. Comput. Graph. 19(9), 1438–1454 (2013). Scholar
  12. 12.
    Lee, Y., Lee, S.: On causality test for time series of counts based on poisson ingarch models with application to crime and temperature data. Commun. Stat.-Simul. Comput. 1–11 (2018)Google Scholar
  13. 13.
    Liboschik, T., Fokianos, K., Fried, R.: tscount: an R package for analysis of count time series following generalized linear models. Universitätsbibliothek Dortmund (2015)Google Scholar
  14. 14.
    MacDonald, B., Ranjan, P., Chipman, H.: GPfit: an R package for fitting a Gaussian process model to deterministic simulator outputs. J. Stat. Softw. 64(12), 1–23 (2015). Scholar
  15. 15.
    Malik, A., Maciejewski, R., Maule, B., Ebert, D.S.: A visual analytics process for maritime resource allocation and risk assessment. In: 2011 IEEE Conference on Visual Analytics Science and Technology (VAST), pp. 221–230 (2011)Google Scholar
  16. 16.
    Plan, E.L.: Modeling and simulation of count data. CPT: Pharmacomet. Syst. Pharmacol. 3(8), 1–12 (2014)MathSciNetGoogle Scholar
  17. 17.
    Razip, A.M., Malik, A., Afzal, S., Potrawski, M., Maciejewski, R., Jang, Y., Elmqvist, N., Ebert, D.S.: A mobile visual analytics approach for law enforcement situation awareness. In: 2014 IEEE Pacific Visualization Symposium, pp. 169–176 (2014)Google Scholar
  18. 18.
    Thomas, R.W., Vidal, J.M.: Toward detecting accidents with already available passive traffic information. In: 2017 IEEE 7th Annual Computing and Communication Workshop and Conference (CCWC), pp. 1–4, January 2017.
  19. 19.
    Towers, S., Chen, S., Malik, A., Ebert, D.: Factors influencing temporal patterns in crime in a large American city; a predictive analytics perspective. SSRN (2016)Google Scholar
  20. 20.
    Yuan, Z., Zhou, X., Yang, T., Tamerius, J., Mantilla, R.: Predicting traffic accidents through heterogeneous urban data: a case study. In: UrbComp 2017 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Pablo Robles
    • 1
  • Andrés Tello
    • 1
  • Lizandro Solano-Quinde
    • 2
    Email author
  • Miguel Zúñiga-Prieto
    • 1
  1. 1.Department of Computer ScienceUniversity of CuencaCuencaEcuador
  2. 2.Department of Electrical, Electronic and Telecommunications EngineeringUniversity of CuencaCuencaEcuador

Personalised recommendations