ARTÍCULO DE CONFERENCIA
Temporal analysis of 911 emergency calls through time series modeling
Fecha
2020Registro en:
978-303032021-8
2194-5357
10.1007/978-3-030-32022-5_13
Autor
Robles Granda, Pablo Dario
Tello Guerrero, Marco Andres
Solano Quinde, Lizandro Damian
Zuñiga Prieto, Miguel Angel
Institución
Resumen
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.